© 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. 12763
    Prev
    Next
    INDEX
    Explanations

    code syntax

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

    The neuron activates on numeric literals (tokens consisting of digits).

    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
    さあ
    -1.25
    踱
    -1.23
    んだよね
    -1.14
    久し
    -1.13
     agencia
    -1.11
    ことができます
    -1.11
    頑張って
    -1.09
    蟎
    -1.08
    さぁ
    -1.08
    Зно
    -1.06
    POSITIVE LOGITS
     to
    1.41
     a
    1.33
    <em>
    1.28
    /
    1.13
    <strong>
    1.10
     (
    1.06
     limão
    1.02
     ‘
    1.01
    Ы
    1.00
     Evidently
    1.00
    Activations Density 0.004%

    No Known Activations