© 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. 216146
    Prev
    Next
    INDEX
    Explanations

    customer service and mentions

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

    sensitive to

    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
    зы
    0.54
    cimientos
    0.48
    ッフ
    0.48
    hydration
    0.47
    ïs
    0.46
    )=[
    0.46
    थि
    0.45
    raction
    0.45
    çou
    0.45
    aison
    0.44
    POSITIVE LOGITS
     hang
    0.53
    挂
    0.51
     separat
    0.50
     hanged
    0.49
     separatist
    0.48
    小组
    0.45
     hangers
    0.45
     Sep
    0.44
    он
    0.44
    大众
    0.44
    Activations Density 0.002%

    No Known Activations