© 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. 203992
    Prev
    Next
    INDEX
    Explanations

    physicists began

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

    influenced by, usage message, ticket #, LEGO houses

    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
     medallion
    0.47
     ukulele
    0.46
    3
    0.43
     kernel
    0.42
     via
    0.42
    激烈
    0.41
     ketogenic
    0.41
     Coaching
    0.41
     connecter
    0.41
     Radiant
    0.41
    POSITIVE LOGITS
    มี
    0.51
    have
    0.51
    จะมี
    0.50
    人は
    0.50
     have
    0.47
    pèce
    0.47
    雳
    0.46
    表現
    0.45
     transgress
    0.45
    ሰው
    0.45
    Activations Density 0.001%

    No Known Activations