© 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. 12078
    Prev
    Next
    INDEX
    Explanations

    numbers and words

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

    The neuron reliably activates on numeric tokens, especially numbers with digits or decimal points.

    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
    s
    0.88
    n
    0.77
    ال
    0.77
    k
    0.77
    c
    0.72
    ist
    0.72
    🛡
    0.70
     основ
    0.68
    kiewicz
    0.68
    <0x80>
    0.68
    POSITIVE LOGITS
     políticos
    0.92
     típico
    0.89
     mínimo
    0.87
     معمولی
    0.84
     Já
    0.81
    ấc
    0.80
     síndrome
    0.79
     совсем
    0.78
     लीजिएगा
    0.78
     меньше
    0.78
    Activations Density 0.000%

    No Known Activations