© 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. 8761
    Prev
    Next
    INDEX
    Explanations

    visual or descriptive nouns

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

    The neuron fires strongly on metadata and byline markers—words like “of,” “by,” “contact,” “posted,” and other tokens that appear in document headers, footers, or author/date/credit lines rather than in main content.

    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
    د
    0.96
    א
    0.73
    ಜ್ಞ
    0.72
    上記の
    0.72
    خ
    0.72
    铛
    0.72
     setembro
    0.71
    ことは
    0.70
    ف
    0.70
     tuổi
    0.69
    POSITIVE LOGITS
     खूबस
    0.87
    iorum
    0.82
    坻
    0.80
    ears
    0.78
    eger
    0.77
    cracker
    0.77
     увели
    0.76
    yson
    0.76
    eas
    0.76
    )`,
    0.75
    Activations Density 0.001%

    No Known Activations