© 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-65K
    4. 15084
    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_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
     事業
    0.59
    addle
    0.54
    ീല
    0.54
     dugg
    0.52
    वाट
    0.50
    콰
    0.49
    ्यानंतर
    0.49
    话说
    0.49
     saying
    0.48
     sabi
    0.46
    POSITIVE LOGITS
    что
    0.58
    OURCES
    0.57
    Paulo
    0.56
    ienka
    0.56
     اذ
    0.55
    propertyName
    0.54
    ENES
    0.54
     RC
    0.54
    ))%>%
    0.54
     GRAY
    0.54
    Activations Density 0.000%

    No Known Activations