© 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. 165004
    Prev
    Next
    INDEX
    Explanations

    breaking laws

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

    destroy trust

    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
     Fing
    0.50
     companhia
    0.46
     الشركة
    0.45
    र्य
    0.45
     Geg
    0.44
     llega
    0.44
     Heg
    0.44
    喲
    0.43
    fé
    0.41
     seules
    0.41
    POSITIVE LOGITS
    cleaning
    0.47
    Cleaning
    0.46
    need
    0.45
    sense
    0.45
     істори
    0.45
     архівів
    0.44
    game
    0.44
    orcid
    0.44
    গায়
    0.43
    primary
    0.43
    Activations Density 0.000%

    No Known Activations