© 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. 148794
    Prev
    Next
    INDEX
    Explanations

    ambassador rightly

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

    translation and context

    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
    нт
    0.54
    ете
    0.50
    ковий
    0.46
    abilis
    0.46
    ак
    0.46
    НЕ
    0.45
    श
    0.45
     extrusion
    0.44
    ਆ
    0.44
    хар
    0.44
    POSITIVE LOGITS
     być
    0.47
    żeli
    0.46
    Hasta
    0.46
     Canarias
    0.45
    Essa
    0.45
     Rouen
    0.45
     Jérôme
    0.44
    points
    0.44
    Nem
    0.44
    点的
    0.43
    Activations Density 0.001%

    No Known Activations