© 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
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-262K
    7. 241395
    Prev
    Next
    INDEX
    Explanations

    characters and roles

    np_max-act-logits · gemini-2.5-flash-lite
    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
     Cannot
    0.57
    🌡
    0.57
     Credentials
    0.57
    ပ
    0.56
    юр
    0.54
    protos
    0.54
    癲
    0.54
     (#
    0.53
    Credentials
    0.53
    по
    0.52
    POSITIVE LOGITS
    compared
    0.67
     brevi
    0.66
     narrator
    0.66
     Tokugawa
    0.62
     Compared
    0.61
     dui
    0.61
     améli
    0.61
    Compared
    0.61
     compared
    0.59
     améliorer
    0.59
    Activations Density 0.000%

    No Known Activations