© 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. 11258
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on the very first content word in each new segment or sentence, marking sentence‐start tokens.

    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
     свойства
    0.85
     Aufnahme
    0.78
     исследования
    0.77
     ограничения
    0.76
     Может
    0.75
     соотно
    0.72
    觜
    0.71
    北海道
    0.70
     constructing
    0.70
    следования
    0.68
    POSITIVE LOGITS
    ol
    0.88
    ρους
    0.82
    ce
    0.81
    ıya
    0.78
     M
    0.77
    ze
    0.75
    olle
    0.75
     choisi
    0.75
     Marca
    0.74
    iy
    0.73
    Activations Density 0.000%

    No Known Activations