© 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. 10-GEMMASCOPE-RES-131K
    7. 100199
    Prev
    Next
    INDEX
    Explanations

    news comes

    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_10/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
    <tr>
    -1.42
     always
    -1.38
     mágica
    -1.30
     about
    -1.30
    ك
    -1.23
    ور
    -1.20
    <td>
    -1.19
    使用的
    -1.19
     rarely
    -1.18
    怱
    -1.18
    POSITIVE LOGITS
     for
    1.46
    Britannique
    1.36
     from
    1.20
    忻
    1.20
    ඥ
    1.18
     zprá
    1.16
     bilgiler
    1.15
    igkeiten
    1.13
    此外
    1.09
     conséquences
    1.09
    Activations Density 0.081%

    No Known Activations