© 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. 128182
    Prev
    Next
    INDEX
    Explanations

    request for service or information

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

    indexes and goals

    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
     시장
    0.56
     цю
    0.55
    ल्पन
    0.55
    ָ
    0.55
     우리가
    0.53
     אז
    0.52
    лке
    0.52
     ರ
    0.51
    വേ
    0.51
     соло
    0.51
    POSITIVE LOGITS
     fireman
    0.42
    lag
    0.42
     trainees
    0.41
     shaved
    0.41
     Canad
    0.41
     Condo
    0.40
    tain
    0.39
    কের
    0.39
     Jacob
    0.39
    unshift
    0.39
    Activations Density 0.000%

    No Known Activations