© 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. 59011
    Prev
    Next
    INDEX
    Explanations

    credit card debts

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

    comments and code explanations

    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
    фар
    0.44
    ӣ
    0.44
    িকভাবে
    0.43
     Петро
    0.43
     Работа
    0.43
    ശാസ്ത്ര
    0.43
    수상
    0.42
    женер
    0.42
    悖
    0.42
    isches
    0.42
    POSITIVE LOGITS
    č
    0.52
    ve
    0.51
    𝗧
    0.51
    š
    0.50
    সল
    0.49
     acompañ
    0.48
     prá
    0.48
    प
    0.47
    ńczy
    0.46
     hidrógeno
    0.46
    Activations Density 0.000%

    No Known Activations