© 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. 77834
    Prev
    Next
    INDEX
    Explanations

    headlights, beams, and flashlights

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

    headlights and flashlights

    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
     நிலையத்தில்
    0.43
    味料
    0.42
    addPreferredGap
    0.42
    ポーツ
    0.42
    ⛪
    0.42
    気の
    0.41
     অধিবেশনে
    0.40
     یخچال
    0.40
    섦
    0.40
    பாட
    0.40
    POSITIVE LOGITS
     headlight
    0.55
     headlights
    0.52
     optic
    0.52
    氙
    0.49
    night
    0.49
     nightly
    0.48
     밤
    0.48
     flashlight
    0.46
     Gorilla
    0.46
     Noct
    0.46
    Activations Density 0.062%

    No Known Activations