© 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. 226640
    Prev
    Next
    INDEX
    Explanations

    numbers and specific phrases

    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
     Messrs
    0.46
     sistema
    0.46
    -
    0.45
     Bonner
    0.43
     crushed
    0.42
     Gilman
    0.42
     oblasti
    0.41
     wasser
    0.41
     ne
    0.41
    系统的
    0.41
    POSITIVE LOGITS
    pF
    0.53
    RSS
    0.47
    лень
    0.46
    u
    0.46
    લું
    0.45
    IS
    0.44
    ISK
    0.44
    (...
    0.42
    ñado
    0.42
    pV
    0.42
    Activations Density 0.000%

    No Known Activations