© 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. 147763
    Prev
    Next
    INDEX
    Explanations

    wide, different, technology, every

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

    phrases or descriptive terms

    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
    Not in Any Lists

    No Comments

    Negative Logits
    েশ্বর
    0.57
    🧖
    0.51
    传感器
    0.49
    বাড়
    0.46
    冷却
    0.46
    ερμαν
    0.46
    ethereum
    0.45
    然而
    0.45
    🚣
    0.44
    JSON
    0.43
    POSITIVE LOGITS
     Inoue
    0.56
     TNF
    0.53
     wondrous
    0.52
     Infinix
    0.52
     JN
    0.52
     UPSC
    0.51
     CNBC
    0.50
     IAEA
    0.50
     myst
    0.49
     invincible
    0.49
    Activations Density 0.001%

    No Known Activations