© 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. 9494
    Prev
    Next
    INDEX
    Explanations

    load _

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

    The main thing this neuron does is detect numeric expressions (numbers, quantities, 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_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
     黃
    0.75
     Immer
    0.74
     Хоро
    0.72
     ইহাতে
    0.71
     һәм
    0.70
     Downloading
    0.70
     پرورش
    0.70
    ্
    0.70
     Под
    0.70
    ুদের
    0.70
    POSITIVE LOGITS
    ugat
    0.82
    étaire
    0.79
    噎
    0.79
    etary
    0.75
    济
    0.74
    ]，
    0.74
    phants
    0.73
    hom
    0.73
    हो
    0.71
    糗
    0.71
    Activations Density 0.001%

    No Known Activations