© 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. 128655
    Prev
    Next
    INDEX
    Explanations

    permission to

    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
    (
    -3.05
    k
    -2.39
     monstre
    -2.33
    gencias
    -2.33
    {
    -2.31
     épisode
    -2.30
     compagnon
    -2.28
     \"
    -2.23
    著名的
    -2.22
    u
    -2.20
    POSITIVE LOGITS
     They
    2.39
    特徴
    2.31
     Their
    2.16
    翾
    2.14
    <td>
    2.14
    ですが
    2.11
     男士
    2.09
    ൅
    2.05
    imgdir
    2.05
    中間
    2.05
    Activations Density 0.008%

    No Known Activations