© 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. 259733
    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
    널
    0.51
    疥
    0.45
    지로
    0.44
    obtain
    0.44
    有好
    0.43
     rulemaking
    0.42
    皇家
    0.42
    走
    0.41
    hiv
    0.41
     activos
    0.41
    POSITIVE LOGITS
     भीड़
    0.51
     場合
    0.48
    ૧
    0.47
     pourrait
    0.45
     ক্ষমা
    0.45
     verurs
    0.44
     könnte
    0.44
     অর্থনীতির
    0.44
    ിയുടെ
    0.44
     voller
    0.44
    Activations Density 0.001%

    No Known Activations