© 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. 14766
    Prev
    Next
    INDEX
    Explanations

    physical location description

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

    The neuron strongly activates on numeric tokens—especially multi­digit numbers with decimal points—i.e. measurements or quantities.

    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
    某个
    0.84
    AD
    0.80
    現在
    0.79
    럼
    0.79
     directement
    0.77
    かせ
    0.77
    '
    0.77
    QU
    0.75
    Q
    0.75
    Av
    0.75
    POSITIVE LOGITS
     КС
    0.82
    таў
    0.79
     Choibalsan
    0.77
     Prand
    0.77
     andDevice
    0.74
     Neend
    0.74
    decken
    0.74
     Cllr
    0.72
     Sunil
    0.72
     Kø
    0.72
    Activations Density 0.000%

    No Known Activations