© 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. 13512
    Prev
    Next
    INDEX
    Explanations

    say digits

    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
     afront
    0.65
     જા
    0.60
     NextResponse
    0.57
     razum
    0.53
     पौराणिक
    0.52
     ግ
    0.52
    ፈል
    0.52
    wanath
    0.51
    ﹌
    0.51
    槍
    0.50
    POSITIVE LOGITS
    inder
    0.52
     undert
    0.52
    成品
    0.51
     साढ़े
    0.50
    att
    0.49
     {:.
    0.48
    subsection
    0.48
    owaniu
    0.48
    μμα
    0.48
     версии
    0.47
    Activations Density 0.196%

    No Known Activations