© 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. 22-GEMMASCOPE-RES-131K
    7. 26708
    Prev
    Next
    INDEX
    Explanations

    Saint, FC, NK, American, Sungai

    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_22/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
     plafon
    -2.36
     célè
    -2.19
     花纹
    -2.05
     obé
    -1.98
     brisa
    -1.98
    扨
    -1.97
     pól
    -1.91
     内衣
    -1.91
     éta
    -1.89
     incrí
    -1.89
    POSITIVE LOGITS
    E
    1.85
    f
    1.84
     for
    1.83
     in
    1.80
    n
    1.80
     all
    1.79
    at
    1.73
    t
    1.73
    w
    1.73
    ;
    1.73
    Activations Density 0.046%

    No Known Activations