© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 194754
    Prev
    Next
    INDEX
    Explanations

    multi-word sequences

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

    new project

    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
     長袖
    0.55
     あ
    0.52
     え
    0.52
    にくい
    0.51
    on
    0.50
     肌
    0.49
     ブルー
    0.49
    ukiyoe
    0.49
     パーカー
    0.48
     ダイニング
    0.48
    POSITIVE LOGITS
    辅助
    0.52
    erin
    0.49
    作为
    0.46
    Während
    0.45
    diam
    0.45
    Esc
    0.44
    藓
    0.44
    issime
    0.44
    issimi
    0.44
    dan
    0.44
    Activations Density 0.000%

    No Known Activations