© 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. 206885
    Prev
    Next
    INDEX
    Explanations

    by clicking

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

    refusal to harmful illegal requests

    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
    ufer
    0.55
    ل
    0.49
    ائلة
    0.49
    لاعب
    0.49
    检验
    0.48
     проверить
    0.48
     Verifica
    0.47
    ümler
    0.47
     Hairst
    0.47
    是将
    0.47
    POSITIVE LOGITS
    getic
    0.46
    },}
    0.45
    ραγ
    0.43
    間で
    0.43
     ਖ
    0.42
    igence
    0.42
    ting
    0.42
    ciation
    0.41
     সতীশ
    0.41
    cation
    0.41
    Activations Density 0.000%

    No Known Activations