© 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. 241565
    Prev
    Next
    INDEX
    Explanations

    diverse world contexts

    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
     phong
    0.62
     dham
    0.61
     renewed
    0.59
    ᄃ
    0.59
     canceled
    0.57
    ]."
    0.54
    "].
    0.52
     paralyzed
    0.52
     coronary
    0.52
     নদ
    0.52
    POSITIVE LOGITS
    чё
    0.56
     छत्तीसगढ़
    0.55
    رآ
    0.55
     전문가
    0.54
     만들기
    0.53
     പക
    0.51
    чён
    0.50
    >/
    0.50
     जुड़ी
    0.50
     ajud
    0.49
    Activations Density 0.003%

    No Known Activations