© 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. 12414
    Prev
    Next
    INDEX
    Explanations

    end of sentence

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

    The neuron strongly activates at the boundaries where spoken lines begin or shift—that is, it picks out the starts (and ends) of dialogue turns.

    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
     [
    0.86
     (
    0.73
     violated
    0.68
     undermined
    0.68
     D
    0.65
     F
    0.63
     interviewed
    0.63
    /
    0.62
     weakened
    0.61
     \[
    0.61
    POSITIVE LOGITS
    ного
    0.84
    Affect
    0.75
     راجس
    0.73
    ная
    0.71
    ні
    0.70
    的他
    0.68
    democracy
    0.68
     என்றார்
    0.67
    他說
    0.66
    обу
    0.66
    Activations Density 0.043%

    No Known Activations