© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9555
    Prev
    Next
    INDEX
    Explanations

    phones numbers

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

    The neuron fires primarily on numeric tokens (multi‐digit numbers, often representing quantities, prices, years, or measurements).

    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
    B
    0.82
    Q
    0.80
    O
    0.80
    K
    0.80
    N
    0.77
    U
    0.77
    T
    0.77
    H
    0.77
    M
    0.75
    E
    0.74
    POSITIVE LOGITS
    Ꮘ
    0.66
    ስማ
    0.57
     disposer
    0.57
     homomorphism
    0.57
     macroscopic
    0.56
     reconciling
    0.56
     perspici
    0.55
     maternelle
    0.55
     mortgagee
    0.55
     ущер
    0.55
    Activations Density 0.113%

    No Known Activations