© 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. 67458
    Prev
    Next
    INDEX
    Explanations

    obtained by

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

    apologies or contrasts

    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
     ಕ
    0.46
    での
    0.44
    '$
    0.43
    Canada
    0.43
    0.43
    un
    0.43
     놓
    0.42
    '{
    0.42
     pravo
    0.42
    高
    0.42
    POSITIVE LOGITS
    olecules
    0.52
    Dirs
    0.45
    ündung
    0.44
    łąd
    0.44
     Neuroscience
    0.44
     Females
    0.44
     Behav
    0.44
    iversity
    0.43
    溇
    0.43
    ifferentiate
    0.43
    Activations Density 0.001%

    No Known Activations