© 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. 6992
    Prev
    Next
    INDEX
    Explanations

    buy or sell

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

    The neuron selectively activates on numeric tokens containing a decimal point (i.e. 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
     Gemeins
    0.84
     ∗
    0.80
     ^
    0.77
    elig
    0.77
    wegs
    0.75
     wissen
    0.74
     ouder
    0.74
     egent
    0.73
    äck
    0.73
     oude
    0.73
    POSITIVE LOGITS
    ي
    0.90
    很多
    0.89
    多家
    0.89
    剧情
    0.88
    민국
    0.84
    严重的
    0.83
    摩托
    0.83
     GPL
    0.82
    בים
    0.81
     시리즈
    0.81
    Activations Density 0.000%

    No Known Activations