© 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. 114192
    Prev
    Next
    INDEX
    Explanations

    in console

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

    direct injection

    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
    列
    0.59
    Примітки
    0.51
    LOLL
    0.50
    त्‍
    0.49
    ADIAN
    0.49
     کاربران
    0.48
     trzec
    0.47
     哦
    0.46
    埓
    0.46
    ATOM
    0.46
    POSITIVE LOGITS
     $
    0.50
     ste
    0.50
    iden
    0.47
     Ste
    0.47
    iring
    0.47
     McIntyre
    0.46
    ilet
    0.45
    ilyn
    0.45
     Tres
    0.45
     Chaque
    0.45
    Activations Density 0.001%

    No Known Activations