© 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. 9809
    Prev
    Next
    INDEX
    Explanations

    before presidents

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

    The neuron fires on tokens that start a new line or segment (i.e. the very first token after a line break).

    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
    0.94
     Jednak
    0.81
     Когда
    0.77
    ac
    0.75
     Když
    0.75
    esterol
    0.75
    »),
    0.73
     I
    0.72
     Однако
    0.72
     ЕС
    0.72
    POSITIVE LOGITS
    тті
    0.85
     heterocyclic
    0.78
    ंदी
    0.73
    घटना
    0.73
    ürm
    0.71
     घरा
    0.71
    ُ
    0.69
    плу
    0.68
    oute
    0.68
    AAAAAAAA
    0.68
    Activations Density 0.000%

    No Known Activations