© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 13435
    Prev
    Next
    INDEX
    Explanations

    math bolding

    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
    uirre
    0.61
    Copper
    0.59
     Copper
    0.57
    ZIONE
    0.57
     якобы
    0.56
    cookie
    0.54
    copper
    0.54
    ᓄ
    0.54
    ীর্ণ
    0.53
    culpa
    0.53
    POSITIVE LOGITS
    mathbf
    1.80
    boldsymbol
    1.54
     mathbf
    1.52
    textbf
    1.25
     bold
    1.16
    bm
    1.15
     벡터
    1.11
    向量
    1.10
     vector
    1.09
     vectors
    1.09
    Activations Density 0.004%

    No Known Activations