© 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. 67341
    Prev
    Next
    INDEX
    Explanations

    own and a descriptor

    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
     of
    -3.58
    ть
    -1.85
    ":
    -1.80
     "
    -1.77
     said
    -1.67
     is
    -1.65
     beberapa
    -1.63
     They
    -1.62
    on
    -1.53
     such
    -1.52
    POSITIVE LOGITS
    珢
    1.75
    Surprisingly
    1.73
    Usually
    1.67
    Ironically
    1.65
    ühungen
    1.62
     tomba
    1.61
    although
    1.60
     mancha
    1.58
    蕯
    1.54
     Hukum
    1.53
    Activations Density 0.009%

    No Known Activations