© 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. 13490
    Prev
    Next
    INDEX
    Explanations

    set symbols

    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
    ാനം
    0.61
    手动
    0.61
    aphyl
    0.56
     lingering
    0.54
     CAGR
    0.54
     VERY
    0.53
     hypotension
    0.53
    哧
    0.53
     judicious
    0.53
    }=-
    0.52
    POSITIVE LOGITS
    -\{
    1.26
    )=\{
    0.98
    ∖
    0.98
    }=\{
    0.97
    setminus
    0.92
    =\{
    0.91
    subset
    0.87
    ∋
    0.79
    ⊂
    0.79
    }=\{\
    0.75
    Activations Density 0.002%

    No Known Activations