© 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. 10-GEMMASCOPE-RES-131K
    7. 124687
    Prev
    Next
    INDEX
    Explanations

    reporting statements

    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_10/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
    了过来
    -1.27
     unseren
    -1.22
    himura
    -1.15
     عمان
    -1.13
     ответил
    -1.13
     our
    -1.12
     ਭ
    -1.11
    onova
    -1.11
     maso
    -1.10
     Now
    -1.09
    POSITIVE LOGITS
     variados
    1.33
     that
    1.32
     said
    1.31
     for
    1.26
     also
    1.24
     even
    1.23
     variadas
    1.22
     however
    1.20
     pokud
    1.20
     čierna
    1.20
    Activations Density 0.086%

    No Known Activations