© 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. 38814
    Prev
    Next
    INDEX
    Explanations

    phrases composed of common words

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

    web technologies and services

    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
    ่ะ
    0.41
    ุม
    0.41
     kato
    0.38
     꿈
    0.38
     prace
    0.38
    枚
    0.38
    ूरिया
    0.37
    尔
    0.37
    元年
    0.37
    ǎ
    0.37
    POSITIVE LOGITS
    setShow
    0.48
     Свет
    0.46
     Владимира
    0.46
    }};
    0.46
     माम
    0.45
     அலங்க
    0.45
    詄
    0.45
     данного
    0.45
    hInstance
    0.44
    Tab
    0.44
    Activations Density 0.001%

    No Known Activations