© 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. 172136
    Prev
    Next
    INDEX
    Explanations

    autonomic nervous system flexibility

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

    enhance detail and specificity

    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
    persky
    0.55
    ،
    0.55
    oczy
    0.50
    legt
    0.48
    owitz
    0.47
    odeled
    0.47
    ，
    0.46
    opensource
    0.45
    opez
    0.44
     soluciones
    0.44
    POSITIVE LOGITS
     minib
    0.57
     localVar
    0.46
     plotter
    0.46
     minif
    0.46
     hurling
    0.45
    袱
    0.45
     Postage
    0.44
     FURTHER
    0.44
     hydrological
    0.44
     mnist
    0.43
    Activations Density 0.001%

    No Known Activations