© 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. 5838
    Prev
    Next
    INDEX
    Explanations

    ghost city, withholding, signals intelligence, frequency, ad tech

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

    The neuron activates on specific named entities and specialized domain or product nouns.

    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
     Quadratic
    0.73
     Diploma
    0.68
    T
    0.66
     Premium
    0.64
     Polynomial
    0.62
     Cavalry
    0.62
     paintball
    0.61
     Railroad
    0.61
     Basketball
    0.61
     Scuola
    0.61
    POSITIVE LOGITS
    _
    0.79
     อื่น
    0.66
    ’
    0.64
     остальные
    0.63
    বাসী
    0.62
    autres
    0.62
     Laufe
    0.61
    本身的
    0.61
    的其他
    0.61
     other
    0.61
    Activations Density 1.125%

    No Known Activations