© 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. 24-GEMMASCOPE-2-RES-16K
    7. 13533
    Prev
    Next
    INDEX
    Explanations

    either/both correlatives

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

    The neuron activates on numeric or quantitative expressions (digits, number words, and related measurement/count contexts).

    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
     aurait
    0.73
    ə
    0.71
     ailleurs
    0.66
    assumption
    0.64
    ला
    0.63
    to
    0.62
    notin
    0.61
    缈
    0.61
    turbine
    0.60
     auraient
    0.60
    POSITIVE LOGITS
     både
    1.56
     zowel
    1.55
     both
    1.54
     sowohl
    1.48
     BOTH
    1.46
    三种
    1.44
     zarówno
    1.36
     سواء
    1.30
    both
    1.28
    无论是
    1.28
    Activations Density 1.039%

    No Known Activations