© 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. 82811
    Prev
    Next
    INDEX
    Explanations

    medical conditions and treatments

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

    oconazole, resin accents, scaling group, defense

    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
     $\
    0.45
    ंगी
    0.45
     Deploy
    0.43
    $\
    0.43
    onan
    0.42
     Trojan
    0.41
     Nil
    0.41
    Id
    0.41
    ^{+}\
    0.41
    ")));
    0.39
    POSITIVE LOGITS
    蹼
    0.50
     ámbito
    0.49
    蕞
    0.46
    炁
    0.46
    rae
    0.46
    decade
    0.45
    romad
    0.45
     extrême
    0.45
    𝚛
    0.45
    ामु
    0.45
    Activations Density 0.000%

    No Known Activations