© 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. 171859
    Prev
    Next
    INDEX
    Explanations

    people, patients, risk, accepts

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

    urban canyon effect, adapt, holds

    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
    ל
    0.55
     MACH
    0.50
    ตำแหน่ง
    0.48
    લ
    0.47
    ล
    0.46
    መር
    0.46
     alimentaires
    0.46
     unités
    0.46
     ironically
    0.45
    ນະ
    0.45
    POSITIVE LOGITS
     Qaraldi
    0.49
    結晶
    0.49
    讫
    0.46
    visitor
    0.45
    Clo
    0.45
    IContainer
    0.44
    cope
    0.43
     cave
    0.43
    ے
    0.43
    WebView
    0.43
    Activations Density 0.000%

    No Known Activations