© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 89647
    Prev
    Next
    INDEX
    Explanations

    >be me,

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    اة
    0.42
    囤
    0.42
     వరకు
    0.40
    යින්
    0.40
     moeilijk
    0.39
     빈
    0.39
     압
    0.39
    他们
    0.39
    Price
    0.38
    వరకు
    0.38
    POSITIVE LOGITS
     поскольку
    0.48
     может
    0.47
    $',
    0.46
     nossa
    0.46
     may
    0.44
     nuestra
    0.44
     оюн
    0.44
     cuyo
    0.43
     потому
    0.43
    тах
    0.43
    Activations Density 0.003%

    No Known Activations