© 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. 31-GEMMASCOPE-2-RES-16K
    7. 10352
    Prev
    Next
    INDEX
    Explanations

    The neuron is highly activated by numeric tokens (especially 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
     Fight
    0.73
    捋
    0.73
     vittoria
    0.67
     theological
    0.67
    Coref
    0.67
     brave
    0.65
    ’
    0.65
     music
    0.64
    сня
    0.64
     climático
    0.64
    POSITIVE LOGITS
    秶
    0.74
    ᆢ
    0.73
     ጡ
    0.71
     ਸਕ
    0.71
     amelyet
    0.70
    芢
    0.70
    ט
    0.69
     cytok
    0.69
     inhom
    0.68
     એન
    0.68
    Activations Density 0.000%

    No Known Activations