© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3811
    Prev
    Next
    INDEX
    Explanations

    The neuron primarily detects decimal number tokens (e.g. floating‐point values, often used for prices or measurements).

    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
     года
    0.79
     состояния
    0.75
     этого
    0.73
     इसी
    0.73
    юще
    0.72
    вый
    0.71
    roč
    0.71
    )$
    0.71
    ющая
    0.70
     своей
    0.70
    POSITIVE LOGITS
     scones
    0.91
     zeros
    0.87
     advantages
    0.85
     overlaps
    0.83
     scrut
    0.82
     dentures
    0.80
     judges
    0.79
     approche
    0.79
     peonies
    0.79
     waffles
    0.78
    Activations Density 0.017%

    No Known Activations