© 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. 3319
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on numeric tokens—particularly decimal 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
    }),
    0.80
    issive
    0.67
    </tr>
    0.64
    ડી
    0.64
    вані
    0.64
    운
    0.64
     giấc
    0.63
     ")");
    0.63
    fficient
    0.61
    Trending
    0.61
    POSITIVE LOGITS
    re
    0.98
    rean
    0.89
     kong
    0.83
     siege
    0.82
    がなく
    0.75
     rey
    0.74
     takeoff
    0.73
    ლ
    0.73
     मेगा
    0.73
    reform
    0.73
    Activations Density 0.000%

    No Known Activations