© 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. 112960
    Prev
    Next
    INDEX
    Explanations

    names and titles

    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
    surate
    -1.88
    0
    -1.58
     {$\
    -1.55
    blers
    -1.45
    стями
    -1.41
     kawaii
    -1.40
    ruptcy
    -1.40
     Rücksicht
    -1.39
     vieles
    -1.39
    amento
    -1.39
    POSITIVE LOGITS
    ↵
    1.86
     MUCH
    1.77
    <bos>
    1.73
     única
    1.63
     fatos
    1.61
    ről
    1.60
    <td>
    1.55
     факты
    1.48
     WHEN
    1.48
     FREE
    1.48
    Activations Density 0.103%

    No Known Activations