© 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. 71324
    Prev
    Next
    INDEX
    Explanations

    time after durations

    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
     będziemy
    -1.29
    に入って
    -1.20
     pezzi
    -1.07
     verschillende
    -1.07
     jesteśmy
    -1.03
     bepaalde
    -1.02
     pureza
    -1.00
    Eug
    -1.00
     entrare
    -0.99
     ibang
    -0.97
    POSITIVE LOGITS
     of
    1.03
    Department
    1.02
    Equal
    0.96
    Recorder
    0.96
    endsection
    0.93
    瞠
    0.93
     kommune
    0.93
    Why
    0.93
     in
    0.92
     atleta
    0.91
    Activations Density 0.104%

    No Known Activations