© 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. 16378
    Prev
    Next
    INDEX
    Explanations

    everyone else

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

    The neuron fires on the last meaningful word before a sentence‐ or section‐ending break, effectively marking the final content token of a segment.

    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
    从
    0.68
     परिस्थितियों
    0.66
     S
    0.64
     R
    0.64
    getResponse
    0.62
     P
    0.61
    your
    0.61
     तुम्हाला
    0.61
    రిగి
    0.61
     करू
    0.60
    POSITIVE LOGITS
     ofthe
    0.87
    .\"
    0.87
    。[
    0.87
    。『
    0.86
    }$.
    0.86
    .[
    0.86
    。“
    0.84
    .[/
    0.84
     ہے۔
    0.83
    .\\
    0.83
    Activations Density 0.288%

    No Known Activations