© 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. 81815
    Prev
    Next
    INDEX
    Explanations

    out of lineup

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

    sensory input

    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
     exercícios
    0.52
     여
    0.47
    Charsets
    0.46
     Ё
    0.46
     ক
    0.46
     coupled
    0.46
     கட்டு
    0.45
     ở
    0.44
     お
    0.44
     čo
    0.44
    POSITIVE LOGITS
    hest
    0.47
     ferv
    0.46
    penny
    0.46
    ised
    0.45
     parlament
    0.45
     commendable
    0.45
     sulfite
    0.45
    性的
    0.44
    spoon
    0.44
     Groupon
    0.43
    Activations Density 0.000%

    No Known Activations