© 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. 220970
    Prev
    Next
    INDEX
    Explanations

    "strings strikers" or specific tokens like "anime episodes"

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

    descriptive continuations

    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
     '\\;'
    0.47
    cknowled
    0.47
    <0xB8>
    0.46
     periodically
    0.46
     lawfully
    0.45
     invoke
    0.45
     manually
    0.44
     জাম
    0.44
    ı
    0.44
    <0x90>
    0.44
    POSITIVE LOGITS
    餌
    0.48
    チャート
    0.47
    楽天市場
    0.47
    ᑖ
    0.46
    バッグ
    0.46
    さら
    0.45
    Olive
    0.45
    捲
    0.45
     거기
    0.45
    ┝
    0.44
    Activations Density 0.001%

    No Known Activations