© 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. 5594
    Prev
    Next
    INDEX
    Explanations

    This neuron detects large numeric tokens, especially multi-digit numbers with 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
    aa
    0.89
    да
    0.84
    mittag
    0.80
     dj
    0.77
     宋
    0.77
    aların
    0.76
    aaaa
    0.75
    dj
    0.75
    સ
    0.73
    drum
    0.73
    POSITIVE LOGITS
     predominate
    0.88
    getResponseCode
    0.84
    КИ
    0.78
    getResult
    0.78
    MLElement
    0.76
     resultSet
    0.75
    ктери
    0.74
    ERVER
    0.73
    யர்
    0.72
     passende
    0.72
    Activations Density 0.000%

    No Known Activations