© 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. 14997
    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
     enc
    0.59
    娑
    0.58
    Ancest
    0.57
    -//
    0.56
     মস্তি
    0.56
     подачи
    0.55
    AssetDiscovery
    0.54
    leb
    0.54
     सुल
    0.54
    NSString
    0.53
    POSITIVE LOGITS
     REALLY
    0.57
     tient
    0.53
     dozen
    0.50
     Its
    0.49
    敀
    0.49
    ОВ
    0.49
     realmente
    0.49
     действительно
    0.49
     оказыва
    0.48
     کوم
    0.48
    Activations Density 0.000%

    No Known Activations