© 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. 178159
    Prev
    Next
    INDEX
    Explanations

    beginning or end of phrases

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

    specific comparisons or characteristics

    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
    ེ
    0.46
    ୍ୟ
    0.44
    小编
    0.43
    鏂
    0.42
    妈妈
    0.42
    卩
    0.41
    了出来
    0.41
    了下来
    0.41
    医学
    0.40
    ियर्स
    0.40
    POSITIVE LOGITS
     conferred
    0.46
     πρώτη
    0.43
    vening
    0.43
    ayed
    0.42
     consultations
    0.40
     پہلی
    0.40
    vanie
    0.40
     sessão
    0.39
     а
    0.39
     applicable
    0.39
    Activations Density 0.000%

    No Known Activations