© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 41-GEMMASCOPE-2-RES-262K
    4. 241372
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_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
    doors
    0.57
     Už
    0.55
    ends
    0.55
     వార
    0.55
    ãos
    0.53
     অভিব্যক্তি
    0.52
     fern
    0.52
    ể
    0.52
    ancia
    0.52
    chloride
    0.52
    POSITIVE LOGITS
     percentages
    0.71
     Jeopardy
    0.70
     Giuliani
    0.70
    ا
    0.70
     Doppler
    0.69
     первой
    0.69
     Deadpool
    0.68
    只有
    0.67
     culprits
    0.66
     eigenvalues
    0.66
    Activations Density 0.000%

    No Known Activations