© 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. 209750
    Prev
    Next
    INDEX
    Explanations

    you have received

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

    people making things

    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
    МІ
    0.48
     دیکھیں
    0.47
     anguish
    0.47
     precarious
    0.46
     precluded
    0.46
     مرکز
    0.45
    Ф
    0.45
     malignant
    0.45
    야
    0.44
     ஏன்
    0.44
    POSITIVE LOGITS
     Rowing
    0.52
     Materials
    0.47
    淡淡
    0.46
     Surfaces
    0.46
     عمر
    0.45
    áž
    0.44
    控股
    0.44
     वाणी
    0.44
    桨
    0.44
     Zimmermann
    0.43
    Activations Density 0.001%

    No Known Activations