© 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. 11867
    Prev
    Next
    INDEX
    Explanations

    banning or prohibiting actions or items

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

    sexually suggestive or abusive

    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
     Konstru
    0.47
     Puede
    0.46
     മനസ്സ
    0.46
     fiecare
    0.45
     വിശ
    0.44
     skillfully
    0.44
     varier
    0.44
    燡
    0.44
     découvre
    0.44
     insign
    0.43
    POSITIVE LOGITS
    禁止
    1.15
     prohibited
    1.05
     banned
    1.04
     запре
    1.00
     prohibiting
    0.98
     నిషే
    0.97
     prohibits
    0.96
     নিষিদ্ধ
    0.96
     banning
    0.93
     禁止
    0.89
    Activations Density 0.120%

    No Known Activations