© 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. 18713
    Prev
    Next
    INDEX
    Explanations

    harmful incidents and casualties

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

    injured people and victims

    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
    mortem
    0.45
    winners
    0.45
    影响
    0.45
    제
    0.45
    Morgan
    0.44
    Opinion
    0.44
    옌
    0.44
    lemy
    0.43
    让
    0.43
    Schneider
    0.43
    POSITIVE LOGITS
     actuellement
    0.56
     ständig
    0.49
     violates
    0.48
     breaches
    0.47
    加入了
    0.47
     allegedly
    0.46
     eingel
    0.45
     évek
    0.45
     emble
    0.45
     constantemente
    0.45
    Activations Density 0.003%

    No Known Activations