© 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. 153472
    Prev
    Next
    INDEX
    Explanations

    directions and travel times

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

    personal and individual journeys

    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
     ibid
    0.48
    ilic
    0.43
     தேசிய
    0.42
    wili
    0.41
    iculares
    0.40
     पढ़ें
    0.40
    葲
    0.39
    icidal
    0.39
    वु
    0.38
     Adult
    0.38
    POSITIVE LOGITS
     ઝ
    0.46
     refinancing
    0.42
    あらゆる
    0.42
    引擎
    0.41
     মাহ
    0.41
    コンパクト
    0.41
    与之
    0.41
    returnValue
    0.40
     ара
    0.39
     quinze
    0.39
    Activations Density 0.001%

    No Known Activations