© 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. 69916
    Prev
    Next
    INDEX
    Explanations

    hides or prevents exposing

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

    protects from exposure

    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
    厚
    0.45
    гант
    0.44
    anyol
    0.42
    Wales
    0.41
    candle
    0.40
    cutter
    0.40
    Castle
    0.40
    цтва
    0.40
    障
    0.40
    thickness
    0.39
    POSITIVE LOGITS
     exposed
    0.85
     Exposed
    0.78
    exposed
    0.73
     exposure
    0.66
     exposing
    0.66
     expose
    0.64
     Exposure
    0.64
     exposes
    0.64
    暴露
    0.63
    露出
    0.59
    Activations Density 0.155%

    No Known Activations