© 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-65K
    7. 15116
    Prev
    Next
    INDEX
    Explanations

    specific items

    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
    টিআই
    0.55
    来る
    0.53
    ជាប់
    0.53
    ilangkan
    0.52
     Arma
    0.52
    哒
    0.51
    釘
    0.51
    mal
    0.50
    ทุก
    0.49
    funk
    0.49
    POSITIVE LOGITS
     desperation
    0.55
     то
    0.55
     શ
    0.55
    શ્ર
    0.55
     lef
    0.54
     pobreza
    0.53
     Ч
    0.52
    Execute
    0.52
    යට
    0.52
    Sharma
    0.52
    Activations Density 0.000%

    No Known Activations