© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 40381
    Prev
    Next
    INDEX
    Explanations

    Razor Pages code documentation

    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
     had
    -1.33
     only
    -1.23
     one
    -1.21
     edif
    -1.14
     juta
    -1.11
    licante
    -1.08
     indah
    -1.07
    álny
    -1.06
     still
    -1.05
     mesin
    -1.04
    POSITIVE LOGITS
     lâng
    0.97
     afore
    0.95
     xt
    0.95
     zvíř
    0.93
     kangaroo
    0.92
     الشباب
    0.92
     réessayer
    0.92
    那么
    0.91
     gluco
    0.90
     パソコン
    0.90
    Activations Density 0.003%

    No Known Activations