© 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. 236935
    Prev
    Next
    INDEX
    Explanations

    bookmarking

    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
     eclipsed
    0.45
    十九
    0.43
    幼
    0.43
    rically
    0.42
     preoccupied
    0.42
     boasted
    0.42
     prominently
    0.41
     altro
    0.41
     ascertaining
    0.41
     banished
    0.41
    POSITIVE LOGITS
    ได้
    0.49
     vindt
    0.49
     ومت
    0.48
    𝙚
    0.48
    埕
    0.47
     लै
    0.47
     nghị
    0.46
     لل
    0.46
    佬
    0.46
     Lào
    0.45
    Activations Density 0.001%

    No Known Activations