© 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. 30198
    Prev
    Next
    INDEX
    Explanations

    playing chess at home

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

    contextual details preceding list items

    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
    Ờ
    0.48
    u
    0.46
    ツ
    0.46
    ক্স
    0.46
    ク
    0.46
    o
    0.46
    পুরা
    0.45
    AssemblyInfo
    0.45
    亞
    0.45
    玄関
    0.44
    POSITIVE LOGITS
     இருந்தால்
    0.52
     incapacitated
    0.46
     انتقال
    0.46
     extinguishing
    0.46
     insufficiency
    0.46
     enraged
    0.45
     interdependence
    0.45
     faulty
    0.45
     incompl
    0.45
     اح
    0.44
    Activations Density 0.000%

    No Known Activations