© 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. 15228
    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
     rogue
    0.61
     XRD
    0.57
    oreal
    0.56
     супер
    0.56
    妾
    0.55
    চ্চার
    0.54
     Nahrung
    0.54
     XLR
    0.54
    パッド
    0.53
     चाइल्ड
    0.53
    POSITIVE LOGITS
    lib
    0.54
    ರುವುದರಿಂದ
    0.54
    𝓵
    0.54
    agn
    0.52
    emene
    0.52
     lib
    0.51
     Calls
    0.51
     Bowers
    0.51
     aus
    0.50
     Call
    0.50
    Activations Density 0.000%

    No Known Activations