© 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. 229544
    Prev
    Next
    INDEX
    Explanations

    hikes or areas

    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
    Consumption
    0.56
    Disconnect
    0.55
     perspici
    0.50
    Configuration
    0.49
    Configure
    0.49
    StartPreview
    0.48
    ﺭ
    0.48
    𝘦
    0.47
    DeleteItem
    0.47
     vincul
    0.47
    POSITIVE LOGITS
     Kohn
    0.47
    i
    0.47
     انشاء
    0.45
     Zheng
    0.44
    inchi
    0.43
     Andrea
    0.43
    osia
    0.43
    as
    0.43
     Yang
    0.42
    inka
    0.42
    Activations Density 0.001%

    No Known Activations