© 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. 253332
    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
    hormat
    0.46
     discussing
    0.43
    hoog
    0.41
    強い
    0.41
    roft
    0.39
     heel
    0.39
     overdue
    0.39
    ⑥
    0.39
     ultimately
    0.38
    強調
    0.38
    POSITIVE LOGITS
     εισ
    0.55
    धारकों
    0.50
     estruturas
    0.48
     configuração
    0.48
     Dolls
    0.47
     زی
    0.46
     Cô
    0.46
    iają
    0.45
    न्यास
    0.45
    لک
    0.45
    Activations Density 0.000%

    No Known Activations