© 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. 216058
    Prev
    Next
    INDEX
    Explanations

    public information in areas

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

    Blue Zones Diet, 12 Angry Men, harvest

    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
    懒
    0.55
    Ӏ
    0.47
     अवकाश
    0.46
    ğun
    0.45
    kak
    0.45
     شا
    0.44
    iousness
    0.44
    品质
    0.44
    嗖
    0.43
     కళ
    0.43
    POSITIVE LOGITS
     nitrogen
    0.58
     electrochemical
    0.57
     separate
    0.56
     experimental
    0.54
     chamber
    0.54
     chemicals
    0.54
     predetermined
    0.54
     climat
    0.53
     environment
    0.52
     hydrogen
    0.52
    Activations Density 0.001%

    No Known Activations