© 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. 44154
    Prev
    Next
    INDEX
    Explanations

    depends on

    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
     for
    -2.50
    cuerdo
    -2.17
     valentín
    -2.14
    ･･
    -2.08
     organizador
    -2.03
    ⃢
    -2.02
     巻き
    -2.02
     土産
    -2.00
     エントランス
    -2.00
     eenvou
    -1.98
    POSITIVE LOGITS
    {
    2.78
     This
    2.55
     was
    2.52
     are
    2.44
    </h2>
    2.44
     will
    2.36
    l
    2.36
    s
    2.28
    *}\
    2.23
    ých
    2.22
    Activations Density 0.001%

    No Known Activations