© 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. 71608
    Prev
    Next
    INDEX
    Explanations

    categories and entities

    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
     katalog
    -1.17
     刷
    -1.13
     nový
    -1.12
     akci
    -1.12
     破解
    -1.12
     komik
    -1.10
     komfor
    -1.09
     optik
    -1.09
     mikrofon
    -1.09
     karton
    -1.08
    POSITIVE LOGITS
     will
    1.29
     and
    1.13
     well
    1.12
     these
    1.09
     tetapi
    1.09
     in
    1.07
     nice
    1.05
     then
    1.05
     because
    1.05
     are
    1.02
    Activations Density 0.001%

    No Known Activations