© 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. 6114
    Prev
    Next
    INDEX
    Explanations

    process and

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

    The neuron flags ordinary content words—common nouns and adjectives carrying the main topic (e.g. “home,” “cost,” “bundles,” “international,” etc.) rather than 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
    irk
    0.78
     حكم
    0.78
     күз
    0.76
    ள
    0.76
     Акы
    0.75
    ู
    0.72
     учетом
    0.72
    vyšší
    0.72
     দক্ষতার
    0.71
    地點
    0.71
    POSITIVE LOGITS
     entra
    0.75
     Immunohist
    0.75
     quae
    0.74
    те
    0.72
     đến
    0.71
    એ
    0.70
     opérés
    0.70
     Enfer
    0.70
     जाएं
    0.69
     เพื่อน
    0.69
    Activations Density 0.001%

    No Known Activations