© 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. 7341
    Prev
    Next
    INDEX
    Explanations

    "attention", "2.", "1.", "amount", "Prevention"

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

    The neuron fires on proper names and named-entity tokens (people, places, organizations, 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
    ல்களில்
    0.59
    bands
    0.56
    riers
    0.54
    ↵↵↵
    0.54
    imus
    0.54
    ลา
    0.53
    ີນ
    0.53
    aints
    0.52
     bands
    0.50
     inferiore
    0.50
    POSITIVE LOGITS
    」、「
    0.77
    )、
    0.63
    ”、“
    0.61
    、『
    0.60
    ),(
    0.58
    )،
    0.56
    丶
    0.56
    》、《
    0.55
    schule
    0.55
     সাহস
    0.54
    Activations Density 0.262%

    No Known Activations