© 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. 175673
    Prev
    Next
    INDEX
    Explanations

    viewing or visiting pages

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

    prediction, materials, flights

    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
    i
    0.46
    ф
    0.43
    زاده
    0.43
    ূন্য
    0.42
    Brand
    0.40
     Rowe
    0.40
     atleta
    0.40
    为
    0.40
    Data
    0.40
     echo
    0.39
    POSITIVE LOGITS
     જેમાં
    0.50
     ファッション
    0.49
     回転
    0.46
     профессор
    0.44
    WithError
    0.44
     မှာ
    0.44
     ગ્ર
    0.44
     ಸಂಬಂಧ
    0.44
     コーヒー
    0.44
     午前
    0.43
    Activations Density 0.001%

    No Known Activations