© 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. 15333
    Prev
    Next
    INDEX
    Explanations

    predicting or classifying items

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

    The neuron fires strongly on the very first “real” content word of each new text block (i.e. the first token after a segment or paragraph boundary).

    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
    middot
    0.80
     Ephesians
    0.78
    میں
    0.73
    ا
    0.72
     शुक्रिया
    0.70
    紀念
    0.70
     imperme
    0.70
    لین
    0.70
    спекти
    0.69
     miei
    0.69
    POSITIVE LOGITS
    $
    0.82
    $}
    0.77
     disposición
    0.77
    $$
    0.73
    Expenses
    0.72
    }$
    0.71
    ‬‬
    0.71
    </span>
    0.70
    +}^{
    0.69
    ดับ
    0.69
    Activations Density 0.000%

    No Known Activations