© 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. 9888
    Prev
    Next
    INDEX
    Explanations

    also lists

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

    The neuron fires on words that occur right after a sentence boundary—that is, it detects sentence-initial tokens.

    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
    又
    0.70
     ايضا
    0.69
    加え
    0.67
     également
    0.66
    また
    0.65
    他又
    0.65
     أيضا
    0.64
    加えて
    0.64
     也
    0.64
     أيضًا
    0.64
    POSITIVE LOGITS
     bukanlah
    0.83
     isn
    0.80
     nėra
    0.79
     değildir
    0.75
     necessitates
    0.71
     disrupts
    0.70
     isnt
    0.69
     bukan
    0.68
     imposes
    0.68
     fluctuates
    0.67
    Activations Density 0.000%

    No Known Activations