© 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. 131039
    Prev
    Next
    INDEX
    Explanations

    embedded devices, services

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

    collects data and links

    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
     Körper
    0.54
    엡
    0.48
    Endpoints
    0.46
    ACTIV
    0.46
    Activ
    0.45
    AppBsky
    0.45
     Bezug
    0.44
    ვე
    0.43
    Caption
    0.43
    MPS
    0.43
    POSITIVE LOGITS
    type
    0.51
    которые
    0.49
    n
    0.49
    ्यांना
    0.47
    nYou
    0.46
     Ophthalm
    0.45
     u
    0.44
    tic
    0.44
     och
    0.44
    dish
    0.44
    Activations Density 0.001%

    No Known Activations