© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 7060
    Prev
    Next
    INDEX
    Explanations

    agreement documents

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

    This neuron fires on the first salient content word or title-like token at the start of a new sentence or section.

    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
    im
    0.84
    ↵
    0.75
    Food
    0.68
    Store
    0.66
     grosses
    0.66
    ail
    0.66
     stal
    0.65
    ie
    0.63
    ţ
    0.63
     ಶಿವ
    0.63
    POSITIVE LOGITS
    tedir
    0.92
     allgemeinen
    0.91
     órganos
    0.91
     сферы
    0.90
     учреждений
    0.89
     artes
    0.87
     óptica
    0.86
    㖑
    0.86
    एशन
    0.85
     Daven
    0.85
    Activations Density 0.000%

    No Known Activations