© 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. 7451
    Prev
    Next
    INDEX
    Explanations

    size comparisons for places

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

    The neuron activates on text specifying essay‐ or writing‐task parameters (e.g. mentions of essay, page or word counts, class or assignment formats).

    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
    $/,
    0.63
    ⁸
    0.62
    ³,
    0.62
     `,
    0.61
     (${
    0.59
     također
    0.57
     Uncomment
    0.57
    ⁵
    0.57
                                   
    0.56
     ใช่
    0.56
    POSITIVE LOGITS
     desar
    0.58
    땠
    0.57
    Mercedes
    0.57
     Rubens
    0.56
    のカ
    0.55
    大き
    0.54
     amely
    0.54
    Porsche
    0.54
     केंद
    0.54
     Porsche
    0.53
    Activations Density 0.042%

    No Known Activations