© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 192871
    Prev
    Next
    INDEX
    Explanations

    escape, urgency, listener, local

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

    prevent, avoid, consistently, secret

    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
    Negative Logits
     ৫৭
    0.54
     frosted
    0.53
    ناول
    0.53
    驄
    0.52
    荕
    0.52
     ৫৮
    0.52
    امي
    0.50
     mixts
    0.49
    鉑
    0.48
     snowboarding
    0.47
    POSITIVE LOGITS
    end
    0.56
    ud
    0.53
    ees
    0.52
    ro
    0.50
    ffer
    0.49
    Understanding
    0.49
    uk
    0.48
    Shel
    0.48
    st
    0.48
    John
    0.48
    Activations Density 0.000%

    No Known Activations