© 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. 112757
    Prev
    Next
    INDEX
    Explanations

    posted in categories

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

    Enumeration, Art Deco, Lemon, lever, estimated, GAN

    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
     delf
    0.54
     iaa
    0.53
    .¹
    0.53
    .+\
    0.53
     LXX
    0.52
     bilingual
    0.52
     graphon
    0.52
     ovu
    0.51
     під
    0.51
    вую
    0.51
    POSITIVE LOGITS
    _
    0.50
    winter
    0.48
    spring
    0.46
    rator
    0.46
    ]{
    0.45
    FLO
    0.45
    distance
    0.44
    isle
    0.44
    冬
    0.43
    _{
    0.42
    Activations Density 0.000%

    No Known Activations