© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15163
    Prev
    Next
    INDEX
    Explanations

    mathematical or code function

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

    The neuron is keyed to picking out major section or paragraph starters—i.e. the first substantive word that begins a new block or heading.

    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
     M
    0.81
     Dys
    0.80
     Auth
    0.79
     MCD
    0.79
     Aug
    0.77
     AC
    0.76
     ARI
    0.76
     Reported
    0.75
     Musica
    0.74
     MN
    0.73
    POSITIVE LOGITS
    TintMode
    0.85
    ссии
    0.84
    >−</
    0.84
    uels
    0.82
    所谓
    0.81
    довать
    0.80
    щать
    0.80
    운데
    0.79
    ্ধে
    0.79
    文件
    0.77
    Activations Density 0.001%

    No Known Activations