© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 144467
    Prev
    Next
    INDEX
    Explanations

    other listeners

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

    discusses concepts, effects, and activities

    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
    Negative Logits
    接近
    0.49
    鐢
    0.47
     वाट
    0.45
    AssemblyInfo
    0.45
    Exposure
    0.44
     നിന്നും
    0.44
    浓度
    0.44
    Percent
    0.44
    getRuntime
    0.44
    ：%
    0.44
    POSITIVE LOGITS
     good
    0.47
     buen
    0.46
    item
    0.46
    transformers
    0.45
    .-\
    0.45
    quela
    0.45
     afterwards
    0.45
     Earth
    0.44
    orems
    0.44
    괜
    0.44
    Activations Density 0.000%

    No Known Activations