© 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. 6998
    Prev
    Next
    INDEX
    Explanations

    react component imports

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

    The main thing this neuron does is detect numeric tokens (numbers, statistics, or measurements) in the text.

    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
    ../../../
    0.93
    ../../
    0.91
     '../../../
    0.89
     '../../
    0.86
    ('../../
    0.84
     ../
    0.72
     '../
    0.71
    ("../../
    0.71
    ../
    0.69
    ('../
    0.67
    POSITIVE LOGITS
     копи
    0.70
     CHAS
    0.64
     Perseverance
    0.61
     dejan
    0.60
     sauvegarde
    0.59
     SCSI
    0.59
     harvesting
    0.59
     Cadastro
    0.58
    চা
    0.57
     ejerc
    0.56
    Activations Density 0.001%

    No Known Activations