© 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. 176990
    Prev
    Next
    INDEX
    Explanations

    conditional language

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

    effects and methodologies

    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
    Saturday
    0.50
    好吃
    0.50
     leider
    0.48
     Leider
    0.46
    ４
    0.46
    wonderful
    0.46
     meravigli
    0.44
    straße
    0.44
    halloween
    0.44
    crist
    0.44
    POSITIVE LOGITS
     محاس
    0.53
     construct
    0.50
     conceptual
    0.46
     appliquée
    0.46
     분석
    0.45
    效应
    0.45
     "@/
    0.44
     விசார
    0.43
    முகச்
    0.43
     transform
    0.43
    Activations Density 0.000%

    No Known Activations