© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 166678
    Prev
    Next
    INDEX
    Explanations

    food, loss, range, leisure

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

    skilled abilities or intelligence

    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
    Negative Logits
     আকার
    0.46
    ہ
    0.46
     evolución
    0.45
    ب
    0.45
     supre
    0.45
    ک
    0.44
     jā
    0.44
     Constable
    0.43
    k
    0.43
     eastbound
    0.43
    POSITIVE LOGITS
    ことなく
    0.45
    হত
    0.44
    이랑
    0.43
    対訳
    0.43
    वृत्ति
    0.42
    經歷
    0.42
     Theological
    0.42
    鐐
    0.42
    टू
    0.41
     competency
    0.41
    Activations Density 0.001%

    No Known Activations