© 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. 9184
    Prev
    Next
    INDEX
    Explanations

    multiple outputs

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

    The neuron fires strongly on numeric list markers (e.g. “1.”) that introduce ordered list items.

    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
    י
    0.90
     Ре
    0.79
     Chron
    0.72
    ுள்ள
    0.70
     вол
    0.68
     ​​
    0.68
     document
    0.68
     j
    0.67
     государство
    0.66
     SP
    0.66
    POSITIVE LOGITS
    NSA
    0.82
    报价
    0.81
    Swami
    0.81
     intolerable
    0.80
    xido
    0.80
    бить
    0.79
    oringa
    0.78
    гови
    0.78
    JSPA
    0.78
     territorio
    0.77
    Activations Density 0.001%

    No Known Activations