© 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. 13997
    Prev
    Next
    INDEX
    Explanations

    complex intellectual

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

    This neuron fires strongly on the very first content token of a new text segment, effectively spotting paragraph or section beginnings.

    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
     vanqu
    0.87
     insurrection
    0.86
    ❗
    0.80
     машин
    0.78
    🙊
    0.76
     Whip
    0.74
    দিনই
    0.73
    тено
    0.72
    ্স
    0.71
    ⸩
    0.71
    POSITIVE LOGITS
    t
    0.91
    e
    0.83
    N
    0.80
    X
    0.80
    3
    0.79
    gu
    0.76
    visions
    0.73
    NI
    0.73
    ト
    0.73
    ti
    0.73
    Activations Density 0.000%

    No Known Activations