© 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. 12010
    Prev
    Next
    INDEX
    Explanations

    foundation models

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

    The neuron activates on numeric tokens—especially multi‐digit numbers, years, volumes, page numbers, and decimal values.

    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
    Pre
    0.72
    𝘖
    0.72
    ort
    0.71
    #__
    0.70
    gom
    0.68
    ile
    0.68
    _
    0.68
    Productions
    0.67
    :
    0.67
    orse
    0.66
    POSITIVE LOGITS
    ፐ
    0.89
    nä
    0.80
    भु
    0.79
    METHODS
    0.77
     연락
    0.77
     pós
    0.76
    roga
    0.76
    ıkl
    0.74
    扯
    0.73
    dominated
    0.73
    Activations Density 0.002%

    No Known Activations