© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 222473
    Prev
    Next
    INDEX
    Explanations

    existing things and their next steps

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

    detailed descriptions of attributes

    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
    Not in Any Lists

    No Comments

    Negative Logits
    दृ
    0.47
    '
    0.47
    एक्स
    0.46
     fieldValue
    0.45
    Sku
    0.45
    浏
    0.44
     sociocultural
    0.44
     nowDate
    0.43
    व्यक्त
    0.42
    าที
    0.42
    POSITIVE LOGITS
     مذ
    0.50
     లే
    0.50
     الل
    0.50
     insuf
    0.48
     رام
    0.47
    𝙡
    0.47
     ف
    0.47
     خل
    0.46
     הל
    0.46
     له
    0.44
    Activations Density 0.000%

    No Known Activations