© 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. 99754
    Prev
    Next
    INDEX
    Explanations

    Athletes and pioneers

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

    image background, join client, lines, numbers

    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
    न्द्र
    0.49
    ουσ
    0.48
    umb
    0.48
     ог
    0.46
    emper
    0.45
    в
    0.44
    ilar
    0.44
    ینه
    0.44
    도를
    0.43
    μα
    0.43
    POSITIVE LOGITS
    zl
    0.48
     Kamil
    0.48
    庆祝
    0.46
     Athlete
    0.45
     Pioneers
    0.45
     Акаде
    0.44
    zp
    0.44
    =|
    0.44
     znak
    0.43
     Athletes
    0.43
    Activations Density 0.000%

    No Known Activations