© 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. 100688
    Prev
    Next
    INDEX
    Explanations

    wishes to answer regarding specific

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

    cannot access

    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
    Сі
    0.64
    าว
    0.55
    ৬
    0.52
    Якщо
    0.51
    ЕН
    0.50
    А
    0.48
    Бар
    0.47
    >]</
    0.46
    می
    0.46
    ୍ର
    0.46
    POSITIVE LOGITS
     بيان
    0.48
    oring
    0.47
     चैन
    0.47
    long
    0.46
     ಸದಸ್ಯ
    0.46
    deserialize
    0.45
    deer
    0.45
     cooperate
    0.44
    lamiento
    0.44
     запол
    0.44
    Activations Density 0.000%

    No Known Activations