© 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. 147506
    Prev
    Next
    INDEX
    Explanations

    technical viewpoint

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

    restoration, carry, maintenance

    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
    เช่น
    0.49
    銭
    0.47
     తగ్
    0.45
     теп
    0.45
    やや
    0.45
     بک
    0.44
    мон
    0.44
     મળ
    0.43
     вари
    0.43
    ೇಶ್
    0.42
    POSITIVE LOGITS
    antam
    0.49
     abilities
    0.49
    kari
    0.46
     excellence
    0.46
    anners
    0.45
    蟳
    0.44
    hi
    0.44
    ||
    0.44
    anner
    0.44
     paintings
    0.43
    Activations Density 0.001%

    No Known Activations