© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 904
    Prev
    Next
    INDEX
    Explanations

    kindred spirit, late detection, falling asleep

    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_34/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
    «
    -0.73
    icked
    -0.73
    Kh
    -0.72
    Подробнее
    -0.72
    &
    -0.72
     提示
    -0.71
    ences
    -0.71
     fewer
    -0.71
     helft
    -0.71
    或
    -0.71
    POSITIVE LOGITS
    Memorials
    0.88
     menyus
    0.83
     quits
    0.82
     dismayed
    0.82
    Flas
    0.79
     *=
    0.79
    ksk
    0.79
    Föld
    0.79
    )};
    0.79
    TokenNameDOT
    0.79
    Activations Density 0.002%

    No Known Activations