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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128590
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on tokens that are units of measurement (e.g. “chains,” “minutes,” “oz,” “days,” “months,” etc.).

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

    units of time and quantity

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    来週
    -1.85
    えっ
    -1.77
    をします
    -1.74
    つづく
    -1.71
    明日は
    -1.69
    さぁ
    -1.67
    にほんブログ村
    -1.66
    あー
    -1.58
    の為
    -1.55
     likely
    -1.54
    POSITIVE LOGITS
    <bos>
    1.78
    ということを
    1.43
    ということです
    1.38
    などが
    1.36
    があります
    1.30
    があり
    1.27
    がありますが
    1.23
    前は
    1.22
    くに
    1.20
    Utilisation
    1.19
    Activations Density 0.004%

    No Known Activations