© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 168521
    Prev
    Next
    INDEX
    Explanations

    common words that start phrases

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

    categorized by

    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
     Гре
    0.43
    лександ
    0.42
    мора
    0.42
     grav
    0.41
    ч
    0.41
     हमे
    0.40
    grav
    0.40
    軒
    0.39
     tom
    0.39
    凱
    0.39
    POSITIVE LOGITS
     ماشینونو
    0.57
     obiettivo
    0.51
     arası
    0.51
     hoặc
    0.50
     teléfonos
    0.49
    場合に
    0.48
    ကလေး
    0.48
     پیسې
    0.47
     खरीदते
    0.47
     lighten
    0.46
    Activations Density 0.001%

    No Known Activations