© 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. 16458
    Prev
    Next
    INDEX
    Explanations

    misappropriating, handling stolen, intentionally killed

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

    deceptive or threatening solicitation

    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
    managerpage
    0.43
     routine
    0.39
    NDAY
    0.38
     script
    0.38
     OEMs
    0.38
     olho
    0.38
    turbine
    0.38
    ྃ
    0.38
    這一
    0.38
     offizi
    0.38
    POSITIVE LOGITS
     имели
    0.45
    usa
    0.42
    ugian
    0.41
     червня
    0.41
    upid
    0.40
     wilfully
    0.40
     }}
    0.40
     obstructing
    0.40
    urahan
    0.39
    urate
    0.39
    Activations Density 0.018%

    No Known Activations