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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 14306
    Prev
    Next
    INDEX
    Explanations

    specific actions/events

    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_65k_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
    NAVIGATION
    0.63
    其
    0.55
    Navigate
    0.55
     यथा
    0.55
    navigation
    0.54
    Nav
    0.53
     سؤال
    0.52
    NAV
    0.52
    navigate
    0.51
    london
    0.51
    POSITIVE LOGITS
    ㄎ
    0.63
    𝘏
    0.62
     Хотя
    0.57
    昷
    0.55
     grammatical
    0.55
     Bateman
    0.55
     Sedangkan
    0.53
    edRight
    0.53
     কৃত
    0.53
    ায়ত্ত
    0.53
    Activations Density 0.000%

    No Known Activations