© 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. 12104
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly responds to emphasis markers—tokens that heighten or intensify the text.

    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
    getStudentNo
    0.86
     Schulen
    0.80
     résulte
    0.78
    quiao
    0.77
    desPort
    0.77
     znači
    0.75
     diesen
    0.73
    㭚
    0.73
    yendo
    0.72
     éxitos
    0.72
    POSITIVE LOGITS
    T
    0.92
    L
    0.86
    D
    0.84
    س
    0.84
     bathroom
    0.81
    E
    0.79
    ప
    0.78
    J
    0.77
    H
    0.77
    కి
    0.74
    Activations Density 0.000%

    No Known Activations