© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 54039
    Prev
    Next
    INDEX
    Explanations

    language codes or syntax elements

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

    The neuron fires on numeric tokens, i.e. standalone numbers or numeric literals.

    oai_token-act-pair · o4-miniTriggered 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
    ofluor
    -1.02
    Ƕ
    -0.97
    五行
    -0.96
    selbst
    -0.94
    endimiento
    -0.94
    Bism
    -0.93
    ”;
    -0.91
    齎
    -0.90
    Tant
    -0.90
    SOCI
    -0.89
    POSITIVE LOGITS
     hugely
    1.07
    をします
    1.07
     Young
    1.03
     копия
    1.01
     سه
    0.98
    Young
    0.96
     amazingly
    0.93
     anyone
    0.91
     anything
    0.91
     ANY
    0.90
    Activations Density 0.006%

    No Known Activations