© 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. 137909
    Prev
    Next
    INDEX
    Explanations

    violations or rules

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

    percentage symbols and scratch

    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
    DO
    0.55
    FE
    0.52
    LEM
    0.52
    H
    0.52
    LAND
    0.51
    DON
    0.51
    K
    0.50
    D
    0.49
    TO
    0.48
    FOR
    0.48
    POSITIVE LOGITS
     maupun
    0.63
     ataupun
    0.53
     حتی
    0.50
     Violation
    0.49
     یا
    0.46
     szabály
    0.46
     violations
    0.45
    regulated
    0.45
     proactive
    0.45
     zelfs
    0.45
    Activations Density 0.000%

    No Known Activations