© 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. 180301
    Prev
    Next
    INDEX
    Explanations

    interest and property

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

    changing emotion or state

    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
     孔
    0.45
    큼
    0.44
    şağı
    0.43
     Robotics
    0.43
    тельных
    0.43
     akong
    0.43
    ный
    0.42
     Freedom
    0.42
    ναν
    0.42
    สัญญา
    0.42
    POSITIVE LOGITS
    сий
    0.47
     потер
    0.46
    Hiện
    0.45
    }<
    0.44
    hoy
    0.44
     ಸೇವ
    0.43
     ند
    0.42
    end
    0.42
     ስርዓ
    0.41
     degeneration
    0.41
    Activations Density 0.000%

    No Known Activations