© 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. 8592
    Prev
    Next
    INDEX
    Explanations

    options, numbers, or size

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

    The neuron is detecting floating‐point numbers (tokens containing a decimal point and digits, e.g. “421.9708”).

    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
    e
    0.89
    le
    0.80
    eud
    0.80
    k
    0.79
    lau
    0.77
    c
    0.77
    u
    0.75
    kyl
    0.75
    button
    0.74
    a
    0.74
    POSITIVE LOGITS
     primos
    0.85
     kc
    0.83
     targets
    0.82
    대상
    0.80
     mythical
    0.79
     otp
    0.79
     tret
    0.78
    ନ୍
    0.77
    驼
    0.77
    ພວກເຮົາ
    0.77
    Activations Density 0.001%

    No Known Activations