© 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. 63154
    Prev
    Next
    INDEX
    Explanations

    WATCH SOME MORE VIDEOS

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

    names and Arabic words

    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
     griseo
    0.46
     arist
    0.44
    ぷ
    0.43
     replicas
    0.42
     tagReport
    0.42
    lbrace
    0.42
    សម្រ
    0.41
    分为
    0.41
     eller
    0.41
     escolher
    0.41
    POSITIVE LOGITS
    Wayne
    0.44
    Lawrence
    0.43
    eren
    0.42
    getOutputStream
    0.41
    湎
    0.41
    Terry
    0.40
    Liam
    0.40
    Sean
    0.39
    Wm
    0.39
    Boston
    0.39
    Activations Density 0.006%

    No Known Activations