© 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. 180213
    Prev
    Next
    INDEX
    Explanations

    contact people or resources

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

    ongoing debate about free choices

    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
    郆
    0.55
    屇
    0.54
     변경
    0.52
     ಬದಲ
    0.50
    峎
    0.49
     আক্রান্ত
    0.47
     punctatis
    0.47
     चित्र
    0.47
    라는
    0.47
    擇
    0.47
    POSITIVE LOGITS
    Able
    0.46
    skills
    0.45
     viciss
    0.44
    ര്‍ഷ
    0.43
     mái
    0.43
    commutative
    0.43
     metre
    0.42
     mediocr
    0.42
    i
    0.42
     thistle
    0.41
    Activations Density 0.000%

    No Known Activations