© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 80614
    Prev
    Next
    INDEX
    Explanations

    Vita version, adopting green

    np_acts-logits-general · gemini-2.5-flash-lite

    more or less

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ),(
    0.48
    哺
    0.46
    tender
    0.44
    сына
    0.43
    ărul
    0.43
    फर
    0.43
    дагы
    0.42
     tender
    0.42
     스마트
    0.42
    辅助
    0.42
    POSITIVE LOGITS
    ан
    0.50
    ASN
    0.48
    soon
    0.47
     Mussolini
    0.46
    /",
    0.46
     Viên
    0.46
     अनुभवों
    0.45
     Ú
    0.45
     CCCC
    0.45
     Filipinos
    0.44
    Activations Density 0.000%

    No Known Activations