© 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. 150944
    Prev
    Next
    INDEX
    Explanations

    non-english words

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

    persona and structure

    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
     P
    0.54
     Illustrations
    0.48
     TEST
    0.48
     Currency
    0.47
    د
    0.47
     QUE
    0.47
     Y
    0.46
     TY
    0.46
    APPLICATION
    0.46
    -
    0.46
    POSITIVE LOGITS
     села
    0.50
    }{{\
    0.50
     trembled
    0.48
     exceptionally
    0.47
     могли
    0.47
     вода
    0.46
    ній
    0.45
     енер
    0.45
     сели
    0.45
     ചേർ
    0.45
    Activations Density 0.000%

    No Known Activations