© 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. 63739
    Prev
    Next
    INDEX
    Explanations

    quantifiable descriptions and specific nouns

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

    lists a term followed by its definition

    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
     טי
    0.55
    ยืน
    0.52
     неожидан
    0.50
     いき
    0.49
    🤣
    0.48
    🕵
    0.48
    🧙
    0.46
     महादेव
    0.46
    🤣🤣
    0.46
    ཆ
    0.46
    POSITIVE LOGITS
     taxable
    0.47
    centage
    0.47
     containing
    0.46
     Shops
    0.44
     Pads
    0.44
     percent
    0.44
     bevat
    0.41
     handful
    0.41
     month
    0.41
     year
    0.40
    Activations Density 0.000%

    No Known Activations