© 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. 183458
    Prev
    Next
    INDEX
    Explanations

    clean and optimize

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

    hostile work environment

    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
     Valves
    0.52
    rows
    0.48
     vért
    0.47
     или
    0.46
     Refriger
    0.46
     Laboratory
    0.45
     Ver
    0.45
     或
    0.45
     Foods
    0.44
     Elev
    0.44
    POSITIVE LOGITS
    ना
    0.49
     legislative
    0.47
     unhappiness
    0.47
     payout
    0.46
     rife
    0.46
     russia
    0.46
     timeframe
    0.46
     stance
    0.45
     hostile
    0.45
     pembang
    0.44
    Activations Density 0.000%

    No Known Activations