© 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. 12101
    Prev
    Next
    INDEX
    Explanations

    by [Name/Title]

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

    The neuron detects document bylines and attribution metadata (e.g., “Reviewed by,” “Author,” “Listed By,” “Verified on,” etc.).

    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
    subscribe
    0.67
    Hibernate
    0.66
    Same
    0.65
    TU
    0.65
    ਰ
    0.65
    Semester
    0.64
    下載
    0.64
    MIN
    0.63
     spør
    0.63
     acess
    0.63
    POSITIVE LOGITS
    জ্জ
    0.71
     Coul
    0.69
     शोभा
    0.68
     Saccharomyces
    0.67
    当時
    0.66
     lepid
    0.65
    :
    0.65
     incred
    0.64
     Opinions
    0.63
    ជ្ជ
    0.63
    Activations Density 0.008%

    No Known Activations