© 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. 176502
    Prev
    Next
    INDEX
    Explanations

    decorative symbols and dividers

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

    SQL ONLY

    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
    0.46
     glTexParameteri
    0.45
     vuccati
    0.45
     তাহাদিগের
    0.45
    াদিগের
    0.44
    দিগকে
    0.44
    盞
    0.44
     codebase
    0.43
     शोषण
    0.43
    舧
    0.43
    POSITIVE LOGITS
    0.53
    ك
    0.50
    “
    0.47
     Ге
    0.43
    ノ
    0.43
    ​
    0.42
    પ
    0.42
    Scope
    0.41
     wholeheartedly
    0.41
    2
    0.41
    Activations Density 0.000%

    No Known Activations