© 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. 176342
    Prev
    Next
    INDEX
    Explanations

    save money or spend less

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

    entity or state descriptors

    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
     arti
    0.49
    ऎ
    0.46
    teles
    0.46
    RESEARCH
    0.45
    テレ
    0.45
     سلاٹ
    0.44
    fta
    0.43
    team
    0.42
    sendBuf
    0.42
     እየሱስ
    0.42
    POSITIVE LOGITS
    ”。
    0.49
    ুট
    0.46
    ”!
    0.46
    构
    0.46
    ogy
    0.45
     Farms
    0.44
     বজায়
    0.43
    ників
    0.43
     Beaux
    0.43
    代码
    0.42
    Activations Density 0.001%

    No Known Activations