© 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. 10884
    Prev
    Next
    INDEX
    Explanations

    sconces or convert, needs space

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

    The neuron strongly activates on infrequent or low-frequency content 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
    的這個
    0.79
    饵
    0.77
    ඬ
    0.77
    alnya
    0.76
    蔥
    0.74
    這次
    0.73
     collecte
    0.73
     végétale
    0.73
    प्लाई
    0.72
    uç
    0.72
    POSITIVE LOGITS
    y
    0.85
    AZ
    0.79
    EL
    0.77
     supernova
    0.74
     ترى
    0.72
    et
    0.71
    AS
    0.71
    ES
    0.71
    SM
    0.71
    tsky
    0.71
    Activations Density 0.000%

    No Known Activations