© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 71737
    Prev
    Next
    INDEX
    Explanations

    but

    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
    توضیحات
    -1.71
     of
    -1.63
     -
    -1.62
    ist
    -1.59
    CurtirCurtir
    -1.43
    お客
    -1.38
     zusätz
    -1.34
    良し
    -1.31
     dlatego
    -1.31
     ermöglich
    -1.31
    POSITIVE LOGITS
    %")
    1.84
     ),
    
    1.82
    埽
    1.76
    EdgeInsets
    1.75
    webElement
    1.71
    ")}
    1.70
    %"),
    1.69
    umerate
    1.69
    </h1>
    1.67
    existsSync
    1.67
    Activations Density 0.027%

    No Known Activations