© 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. 34393
    Prev
    Next
    INDEX
    Explanations

    name said

    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
     kupa
    -1.16
    參考文獻
    -1.02
     sezonu
    -0.93
     usługi
    -0.91
    ẓ
    -0.90
    leggen
    -0.89
    nieuw
    -0.88
    hadapi
    -0.88
    wortet
    -0.88
    autoIncrement
    -0.88
    POSITIVE LOGITS
     said
    1.38
     also
    1.08
    還能
    1.02
    還可以
    1.02
     lekko
    1.00
    URBANA
    0.99
     alfo
    0.98
     diminuer
    0.96
     sagte
    0.96
     CULTURAL
    0.96
    Activations Density 0.020%

    No Known Activations