© 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. 6386
    Prev
    Next
    INDEX
    Explanations

    folder management

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron activates on numeric expressions—tokens representing numbers or numeric data.

    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
    ం
    0.83
     û
    0.76
    పై
    0.73
     enjoin
    0.70
    ܢܐ
    0.70
     －
    0.69
     مقر
    0.69
     деца
    0.69
     ن
    0.68
     meni
    0.68
    POSITIVE LOGITS
    suitcase
    0.90
     randomness
    0.85
    IDENTAL
    0.83
    দীন
    0.82
    ?).
    0.81
    Ive
    0.80
    AYS
    0.80
    FIELD
    0.79
    লির
    0.79
    REFLECTION
    0.79
    Activations Density 0.000%

    No Known Activations