© 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. 260369
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    τώ
    0.51
     uczniów
    0.50
     الدنيا
    0.50
     duas
    0.48
     vernacular
    0.47
    诺
    0.46
     lembra
    0.45
     ustawy
    0.45
     ouders
    0.44
     නි
    0.44
    POSITIVE LOGITS
    ohid
    0.45
     agreed
    0.44
    říve
    0.44
    urator
    0.42
     queried
    0.42
    ázky
    0.41
     argued
    0.41
    깅
    0.41
    гор
    0.40
     accrued
    0.40
    Activations Density 0.000%

    No Known Activations