© 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. 24-GEMMASCOPE-2-RES-16K
    7. 11931
    Prev
    Next
    INDEX
    Explanations

    clearance or conflict

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

    The neuron responds strongly to tokens that represent numeric values—especially multi‐digit or decimal figures.

    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
    𝙀
    0.90
    ి
    0.87
    EDUCATION
    0.81
    IONS
    0.80
    ে
    0.80
    Menurut
    0.79
    𝓖
    0.79
    近年
    0.77
    Meesho
    0.77
     नॉन
    0.77
    POSITIVE LOGITS
    ৪০
    0.79
    の両
    0.76
    ў
    0.75
    ubble
    0.73
     Nb
    0.71
     высоко
    0.71
    /(
    0.70
    ৪১
    0.70
    did
    0.68
    ic
    0.67
    Activations Density 0.000%

    No Known Activations