© 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. 16030
    Prev
    Next
    INDEX
    Explanations

    features, albums, or items

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

    explaining complexity and use cases

    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
     fáciles
    0.54
    ímos
    0.45
    íta
    0.44
     सच्चे
    0.44
    íonn
    0.44
     jamás
    0.44
    ਦ
    0.43
     cientos
    0.43
    佯
    0.42
    illes
    0.42
    POSITIVE LOGITS
     Implications
    0.50
     suggesting
    0.48
     implications
    0.47
     screwdriver
    0.45
     beyond
    0.44
     Auswirkungen
    0.44
     mentioning
    0.43
     Schra
    0.43
     باستخدام
    0.43
     Reactions
    0.43
    Activations Density 0.000%

    No Known Activations