© 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. 63416
    Prev
    Next
    INDEX
    Explanations

    numbers followed by colon

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

    progression or migration

    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
     diminta
    0.48
     oth
    0.44
     blot
    0.42
     tenacious
    0.41
     interfacing
    0.41
     lease
    0.40
    痂
    0.40
     मेहन
    0.39
    লাকে
    0.39
     jednostavno
    0.39
    POSITIVE LOGITS
    ಅ
    0.54
    а
    0.48
    Обра
    0.46
    Архи
    0.46
    ה
    0.46
    Configs
    0.45
    Football
    0.45
    |\
    0.45
    О
    0.44
    До
    0.43
    Activations Density 0.000%

    No Known Activations