© 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. 10501
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates around numeric measurements or quantities (i.e. tokens in contexts with numbers/metrics).

    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
    らった
    0.82
     вопросам
    0.80
    ਆਂ
    0.80
    сное
    0.77
     silicone
    0.75
    s
    0.73
    Foldout
    0.73
     scholar
    0.72
    чный
    0.72
     mnemonic
    0.72
    POSITIVE LOGITS
     Sincerely
    0.77
     assolutamente
    0.73
     тобто
    0.71
     addirittura
    0.71
     absolument
    0.70
     armado
    0.69
     yakni
    0.68
    न
    0.68
    inerja
    0.67
     iaitu
    0.67
    Activations Density 0.000%

    No Known Activations