© 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. 128133
    Prev
    Next
    INDEX
    Explanations

    Persian, Pashto, Swahili, Hindi, Spanish, English, Cyrillic, Korean

    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
    only
    -1.99
    НИМА
    -1.80
     eſſ
    -1.77
     серебри
    -1.69
    !");
    -1.66
    ことも
    -1.60
     небольшой
    -1.59
    珢
    -1.59
     everything
    -1.59
    therefore
    -1.59
    POSITIVE LOGITS
     muhimu
    1.97
     of
    1.88
     nyingi
    1.73
     yore
    1.69
    उत्तर
    1.55
    Hermoso
    1.53
     nzuri
    1.53
     ikiwa
    1.52
     kubwa
    1.52
     maroon
    1.49
    Activations Density 0.002%

    No Known Activations