© 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. 96708
    Prev
    Next
    INDEX
    Explanations

    unlawful or complex behavior

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

    retrieving sensitive data

    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
    as
    0.65
    olda
    0.52
    plant
    0.52
    water
    0.52
    4
    0.52
    aso
    0.49
    ood
    0.49
    soft
    0.49
    real
    0.49
    ma
    0.49
    POSITIVE LOGITS
     autistic
    0.58
     arrogant
    0.57
     ekran
    0.55
     inscri
    0.54
     parall
    0.54
    ﹁
    0.52
     unlawful
    0.51
     reckless
    0.51
     antisocial
    0.51
     экрана
    0.50
    Activations Density 0.000%

    No Known Activations