© 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. 141295
    Prev
    Next
    INDEX
    Explanations

    post or upload content

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

    after quotation marks

    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
     konu
    0.47
     GK
    0.43
     invester
    0.43
     GCP
    0.43
    谌
    0.43
     salesperson
    0.42
     दैन
    0.42
     primeiro
    0.41
    ؤال
    0.41
     GMP
    0.41
    POSITIVE LOGITS
     blocks
    0.52
    blocks
    0.48
    块
    0.46
     ఏర్
    0.45
     Blocks
    0.45
    pieces
    0.45
    が必要
    0.45
     мүм
    0.43
    restrictions
    0.43
    menus
    0.43
    Activations Density 0.001%

    No Known Activations