© 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. 6986
    Prev
    Next
    INDEX
    Explanations

    security border

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

    The neuron is sensitive to numeric tokens containing decimal points (floating‐point numbers).

    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
     RSC
    0.82
    Aud
    0.78
    поле
    0.78
    omon
    0.77
    masa
    0.75
    ಛ
    0.75
    OCS
    0.74
     Rosh
    0.73
     Maus
    0.73
    CRO
    0.73
    POSITIVE LOGITS
     통
    0.76
     ترد
    0.76
     Фурга
    0.70
     해
    0.70
     ದ
    0.67
     frein
    0.67
     அழைத்து
    0.64
     resultMap
    0.64
     brinqu
    0.63
     민
    0.63
    Activations Density 0.000%

    No Known Activations