© 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. 219671
    Prev
    Next
    INDEX
    Explanations

    decision after, decreases their, candle, my experience, deducting

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

    conversational hypnosis works

    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
    denom
    0.45
     Bata
    0.43
     ش
    0.43
     Marx
    0.41
     قر
    0.41
    ta
    0.41
     Sch
    0.41
     ஏற்க
    0.40
     Squire
    0.40
    glyphs
    0.40
    POSITIVE LOGITS
     attaque
    0.54
    瘁
    0.53
    自从
    0.52
    时候
    0.48
     doet
    0.47
     organización
    0.47
    を見て
    0.46
     organization
    0.45
     aussi
    0.45
    Vec
    0.45
    Activations Density 0.000%

    No Known Activations