© 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. 13641
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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
    OfDeath
    0.54
    gekehrt
    0.52
     hinn
    0.51
    odend
    0.51
    Lists
    0.51
     ત
    0.50
     Lists
    0.50
     curto
    0.49
    Sorted
    0.49
     дър
    0.48
    POSITIVE LOGITS
    Diagonal
    0.56
    Santos
    0.55
    全是
    0.54
     Morse
    0.52
     remise
    0.52
    Morse
    0.52
    ாட்ட
    0.51
    تقرير
    0.51
    ₤
    0.51
    diag
    0.50
    Activations Density 0.000%

    No Known Activations