© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129712
    Prev
    Next
    INDEX
    Explanations

    trade-offs

    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
     दोनों
    -1.08
     bz
    -0.95
     nhat
    -0.92
    関連リンク
    -0.87
    lné
    -0.85
    Both
    -0.82
    wsj
    -0.82
    ковь
    -0.81
    msgid
    -0.80
    CommandHandler
    -0.80
    POSITIVE LOGITS
     lastly
    1.64
     Lastly
    1.28
    these
    1.19
    Lastly
    1.13
     these
    1.12
     ExecuteAsync
    1.09
     наконец
    1.07
    了过来
    1.05
    tım
    1.05
     unless
    1.03
    Activations Density 0.001%

    No Known Activations