© 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. 31-GEMMASCOPE-2-RES-16K
    7. 6468
    Prev
    Next
    INDEX
    Explanations

    This neuron activates when it encounters numeric tokens with decimal points (floating-point 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_31_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
     Росії
    0.87
     Що
    0.84
    וו
    0.78
     shir
    0.77
    Ի
    0.77
    痣
    0.76
    Թ
    0.75
     技術
    0.73
    ┏
    0.73
     шуда
    0.73
    POSITIVE LOGITS
    oke
    0.86
    nte
    0.82
    rate
    0.77
    id
    0.76
    ise
    0.76
    get
    0.75
    ke
    0.73
    rd
    0.73
    ont
    0.72
    hase
    0.72
    Activations Density 0.000%

    No Known Activations