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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14135
    Prev
    Next
    INDEX
    Explanations

    border-radius values

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires most strongly on numeric values specifying radii or rounded‐corner dimensions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
    Salut
    0.77
     Eugenia
    0.74
    rowData
    0.67
    SERVIDOR
    0.66
    叫做
    0.65
     Algon
    0.65
    榉
    0.64
    serialization
    0.64
    ázky
    0.63
     arbe
    0.63
    POSITIVE LOGITS
     nessuna
    0.88
     centerX
    0.84
    圓
    0.82
     convexes
    0.79
     internacionais
    0.79
     migliori
    0.78
    KS
    0.77
    AD
    0.76
    HS
    0.75
     個
    0.75
    Activations Density 0.023%

    No Known Activations