© 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. 13970
    Prev
    Next
    INDEX
    Explanations

    cooking instructions, durations, or locations

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

    The neuron is specialized to detect numeric tokens—particularly floating-point numbers or statistical values.

    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
    ⼈
    0.81
    executable
    0.76
    Ἐ
    0.75
    娩
    0.74
     falando
    0.73
    Quan
    0.73
    いく
    0.72
    sentences
    0.72
    readlines
    0.72
    ریک
    0.72
    POSITIVE LOGITS
    о
    0.74
    цэ
    0.74
     ощущение
    0.73
     россия
    0.73
    lla
    0.71
     wzgl
    0.71
    2
    0.69
    ин
    0.68
    7
    0.68
    ից
    0.68
    Activations Density 0.000%

    No Known Activations