© 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. 183387
    Prev
    Next
    INDEX
    Explanations

    little regard

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

    weather and physical attributes

    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
    ές
    0.46
     शेखर
    0.46
    щиеся
    0.44
     איז
    0.43
     साग
    0.42
     उमर
    0.42
     ㅅ
    0.41
     sportsman
    0.41
     Эд
    0.41
     Никола
    0.40
    POSITIVE LOGITS
    餬
    0.49
     Kyiv
    0.47
     geopol
    0.47
    imetry
    0.46
     Ukrainians
    0.45
    女性
    0.45
    addPreferredGap
    0.45
     adolescents
    0.44
    階段
    0.44
    ravity
    0.44
    Activations Density 0.002%

    No Known Activations