© 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. 91198
    Prev
    Next
    INDEX
    Explanations

    specific contexts

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

    complexity, suits, rush, hue, vapor

    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
    cardia
    0.45
    ловой
    0.44
    ња
    0.42
     dood
    0.42
     It
    0.41
    媜
    0.41
     łat
    0.40
    িলিয়া
    0.40
    鹅
    0.40
    ϳ
    0.40
    POSITIVE LOGITS
    už
    0.55
    proble
    0.52
    別の
    0.49
     ಆರಂಭ
    0.48
     குறை
    0.48
     previsto
    0.46
     Einen
    0.46
     문제가
    0.45
     проблему
    0.45
     Optionen
    0.45
    Activations Density 0.002%

    No Known Activations