© 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. 209086
    Prev
    Next
    INDEX
    Explanations

    legal actions and consequences

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

    Reduced Corruption

    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
     luxurious
    0.53
     q
    0.48
     demand
    0.47
     luxury
    0.44
    L
    0.43
    Main
    0.43
    October
    0.43
     premium
    0.42
    ^{\
    0.41
    HEALTH
    0.41
    POSITIVE LOGITS
    وری
    0.49
    кової
    0.48
     سیستم
    0.46
     จน
    0.46
    wirk
    0.46
     czynności
    0.45
    KSprite
    0.45
    czeń
    0.45
    кови
    0.44
     คลิป
    0.44
    Activations Density 0.001%

    No Known Activations