© 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. 7535
    Prev
    Next
    INDEX
    Explanations

    google, github, links

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

    This neuron fires strongly on numeric tokens and number-like sequences (digits, decimals, 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
    ondale
    0.73
    驊
    0.68
    ynu
    0.67
    まります
    0.67
    cludes
    0.66
    snp
    0.66
    anee
    0.66
    𝓑
    0.65
     పెరుగు
    0.65
    inea
    0.64
    POSITIVE LOGITS
     hiểm
    0.88
     Armenian
    0.86
     Armenians
    0.86
     Charan
    0.84
     Aryan
    0.81
     Zoro
    0.77
     Daim
    0.75
     alkalies
    0.75
     Fuer
    0.75
     بعض
    0.74
    Activations Density 0.000%

    No Known Activations