© 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. 201986
    Prev
    Next
    INDEX
    Explanations

    acoustical, series, screens, frames

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

    now, earlier, or later

    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
     پن
    0.51
     and
    0.50
    징
    0.49
    clos
    0.48
    praw
    0.47
    aaf
    0.47
    alz
    0.46
    alities
    0.46
    and
    0.45
    alm
    0.45
    POSITIVE LOGITS
    cię
    0.48
     milj
    0.47
    ทำให้
    0.46
    伱
    0.46
    的海
    0.45
     gespielt
    0.45
     Bakın
    0.45
     eléctrica
    0.44
    龙头
    0.44
     নিয়ন্ত্রণ
    0.44
    Activations Density 0.001%

    No Known Activations