© 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. 5267
    Prev
    Next
    INDEX
    Explanations

    predictable

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

    The neuron fires on content‐heavy, domain‐specific nouns (often multi-syllabic or hyphenated), distinguishing them from common function words.

    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
    ี
    0.84
    های
    0.77
    晗
    0.76
    ethi
    0.75
    ヶ月
    0.73
    禧
    0.73
    ১
    0.70
    はや
    0.70
    ról
    0.70
    哒
    0.69
    POSITIVE LOGITS
     සඳ
    0.78
    bore
    0.77
    sponsored
    0.77
    atmosphere
    0.76
    collectionView
    0.76
    pport
    0.75
    customize
    0.75
    sack
    0.75
    accept
    0.74
     Atmosphere
    0.73
    Activations Density 0.000%

    No Known Activations