© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 69050
    Prev
    Next
    INDEX
    Explanations

    mathematical or code expressions

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on numeric tokens (digits and numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    mathematical symbols and variables, particularly in the context of mathematical notation like backslashes, dollar signs, and single-letter variables.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    mathematical notation in LaTeX-style expressions, especially single-letter variables, set/group symbols, and operators in formal statements.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <_>
    -1.11
     länder
    -1.10
     Corée
    -1.04
     torsdag
    -1.01
    сили
    -1.00
    сить
    -0.99
    Bjs
    -0.99
    ὠ
    -0.97
     gebo
    -0.96
     pengar
    -0.95
    POSITIVE LOGITS
     if
    1.30
     that
    1.09
    complish
    1.01
     our
    0.99
     because
    0.95
     this
    0.94
     Sélectionnez
    0.93
    これからも
    0.92
     проє
    0.89
    indeki
    0.88
    Activations Density 0.004%

    No Known Activations