© 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. 252438
    Prev
    Next
    INDEX
    Explanations

    competitive evaluation needs

    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
    ли
    0.56
    Mockito
    0.52
    RxDocument
    0.50
    ાર્થી
    0.50
    eneva
    0.50
    Maven
    0.50
    itaire
    0.50
    呑
    0.49
    ǎo
    0.48
     শাসক
    0.48
    POSITIVE LOGITS
     exclusive
    0.46
     دادن
    0.46
     wie
    0.45
     ‚
    0.45
     wart
    0.42
    ‚
    0.42
     telegraph
    0.42
     tepl
    0.41
     Raster
    0.41
     exclusivity
    0.41
    Activations Density 0.000%

    No Known Activations