© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 135326
    Prev
    Next
    INDEX
    Explanations

    Dark Humor, renal failure, enzymatic cleaners

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ゴ
    0.48
    SYSTEM
    0.46
     hyg
    0.46
    لان
    0.44
     мони
    0.44
     オリ
    0.43
    的な
    0.43
    사업
    0.43
    स्टोन
    0.42
    𝒽
    0.42
    POSITIVE LOGITS
     পাপ
    0.42
     Texts
    0.40
     ordinaire
    0.40
    renner
    0.40
    च्चय
    0.40
     bew
    0.39
     bekannt
    0.39
     and
    0.38
     Bankruptcy
    0.38
    odie
    0.38
    Activations Density 0.000%

    No Known Activations