© 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. 11964
    Prev
    Next
    INDEX
    Explanations

    usually followed by punctuation or specific words

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

    The neuron fires strongly on the very first substantive token in each new text segment (i.e. the opening word of a paragraph or block).

    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
    ﻑ
    0.88
     semelhantes
    0.86
     neste
    0.85
     deste
    0.84
     chooser
    0.84
     следует
    0.83
     различные
    0.83
    чает
    0.82
     zorgt
    0.81
     Foli
    0.81
    POSITIVE LOGITS
    ear
    0.77
    ımda
    0.77
    اج
    0.75
    piration
    0.75
    ە
    0.75
    चा
    0.74
    ំនួន
    0.73
    ӧ
    0.72
    opsis
    0.71
    चे
    0.71
    Activations Density 0.000%

    No Known Activations