© 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. 31-GEMMASCOPE-2-RES-16K
    7. 10157
    Prev
    Next
    INDEX
    Explanations

    superscripts, numbers, and mathematical notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_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
    heated
    0.66
    ½
    0.63
     CSA
    0.58
     anch
    0.57
    lje
    0.54
     пів
    0.54
     dv
    0.54
     ½
    0.53
     halv
    0.52
     polov
    0.52
    POSITIVE LOGITS
    ⁶
    0.69
     zeros
    0.67
    ⁴
    0.67
    ³,
    0.64
    ³
    0.63
    ⁹
    0.61
    ³.
    0.61
    ˄
    0.61
    ⁷
    0.59
     zeroes
    0.57
    Activations Density 0.028%

    No Known Activations