© 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. 11506
    Prev
    Next
    INDEX
    Explanations

    website domain extensions

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

    domain names followed by slashes

    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
     போல்
    0.43
     云
    0.41
     ആക
    0.41
     Spreadsheet
    0.40
    ್ಧ
    0.40
    投标文件
    0.40
    ীবন
    0.40
    ={}
    0.39
     ബി
    0.39
    =[]
    0.39
    POSITIVE LOGITS
    /
    0.55
    /...
    0.43
     salt
    0.41
    //
    0.41
     (“
    0.41
     mastic
    0.39
     population
    0.38
     cadre
    0.38
     gamut
    0.38
     pys
    0.37
    Activations Density 0.011%

    No Known Activations