© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 12755
    Prev
    Next
    INDEX
    Explanations

    run in a circle

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

    The neuron fires strongly on colon punctuation (the “:” token).

    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
    ing
    1.98
    ния
    1.59
    ae
    1.58
    ة
    1.58
    [[
    1.55
    ியே
    1.54
    :
    1.49
    のが
    1.45
    ington
    1.38
     வகையில்
    1.38
    POSITIVE LOGITS
    ট
    1.85
    ਕ
    1.55
    dokkaHtml
    1.45
    ")))
    1.41
    jenja
    1.41
    مر
    1.38
    א
    1.38
    """"
    1.35
     PropTypes
    1.30
    س
    1.29
    Activations Density 0.307%

    No Known Activations