© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 40304
    Prev
    Next
    INDEX
    Explanations

    category labels

    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
    ilitary
    -1.02
    स्ता
    -1.02
     Ejemplo
    -1.01
    慢慢的
    -0.98
     удалось
    -0.98
     Puede
    -0.97
    rean
    -0.96
     ДА
    -0.96
    istor
    -0.95
    UDE
    -0.93
    POSITIVE LOGITS
    misc
    1.21
     during
    1.20
     uses
    1.10
     miscellaneous
    1.09
     commonly
    1.09
     often
    1.05
     various
    1.04
     all
    1.04
     generally
    1.02
     will
    1.02
    Activations Density 0.134%

    No Known Activations