© 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. 31-GEMMASCOPE-2-RES-16K
    7. 8032
    Prev
    Next
    INDEX
    Explanations

    Roblox scripts

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

    The neuron spotlights numeric answer outputs—especially standalone numbers or calculated values (often with decimals) in problem‐solving or measurement contexts.

    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_31_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
     preparar
    0.58
     gauze
    0.56
    Gambar
    0.55
     prepara
    0.55
    }-\
    0.52
     tqdm
    0.52
     $=\
    0.51
     dikkat
    0.51
    {}",
    0.51
     configurar
    0.50
    POSITIVE LOGITS
     Hope
    0.74
    hope
    0.72
     hope
    0.72
     trillion
    0.69
     nadzie
    0.69
     esperanza
    0.67
     مليون
    0.66
    Hope
    0.63
     yan
    0.63
     вроде
    0.60
    Activations Density 0.025%

    No Known Activations