© 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. 75350
    Prev
    Next
    INDEX
    Explanations

    Auto DS / anti-

    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
     of
    -1.24
     whose
    -1.19
     to
    -1.19
     each
    -1.14
     in
    -1.13
     will
    -1.12
     simply
    -1.02
     milyon
    -0.99
    罰
    -0.98
    もしくは
    -0.95
    POSITIVE LOGITS
    皷
    1.25
     considérée
    1.09
     WRITER
    1.05
    졍
    1.04
    Gön
    1.02
     then
    1.01
    に戻る
    1.00
    際に
    1.00
    푉
    0.99
    ftar
    0.98
    Activations Density 0.003%

    No Known Activations