Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11794
    Prev
    Next
    INDEX
    Explanations

    не, não

    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
    quelize
    -2.67
    izoen
    -2.28
    事態
    -2.20
    brtc
    -2.20
     constater
    -2.20
    前は
    -2.16
     imperio
    -2.14
    <bos>
    -2.06
    tembro
    -2.05
    zembro
    -2.03
    POSITIVE LOGITS
    ра
    2.16
    H
    2.16
    {
    2.06
     necessarily
    2.05
    <em>
    2.03
    <u>
    2.02
    ching
    1.97
    ,
    1.95
    </b>
    1.94
    <b>
    1.89
    Activations Density 0.006%

    No Known Activations