© 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. 187330
    Prev
    Next
    INDEX
    Explanations

    talking about you or I

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

    various metrics and conditions

    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
     সংযোগ
    0.51
     tương
    0.49
     thứ
    0.47
     ቦታ
    0.46
     بي
    0.46
     అనే
    0.45
    бие
    0.45
     repudiandae
    0.45
     शेयर
    0.44
     계
    0.44
    POSITIVE LOGITS
    薊
    0.47
     গেরিলাদের
    0.43
     for
    0.43
    ッチン
    0.43
    তীশ
    0.42
    for
    0.42
    ாட
    0.42
     WAIT
    0.42
    vation
    0.41
    HELLO
    0.41
    Activations Density 0.001%

    No Known Activations