© 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. 39885
    Prev
    Next
    INDEX
    Explanations

    product shown, teach, complicated

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

    offer suggestions or ask questions

    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
    verk
    0.46
    RetResult
    0.45
    not
    0.44
     verk
    0.44
    wan
    0.43
    DVD
    0.43
    USB
    0.43
    ﻥ
    0.43
    acerb
    0.43
    Verlag
    0.43
    POSITIVE LOGITS
     FODC
    0.61
     habitats
    0.55
     ecosystem
    0.53
     behaviours
    0.53
     memorable
    0.52
     খাজ
    0.52
     FOOD
    0.50
     reimag
    0.49
     characteristics
    0.48
     gardeners
    0.48
    Activations Density 0.000%

    No Known Activations