© 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. 13262
    Prev
    Next
    INDEX
    Explanations

    The neuron spikes on the very first substantive word of each new text segment or paragraph.

    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
    ႄ
    0.75
     страни
    0.73
     dicen
    0.72
    validacion
    0.71
    AMENTE
    0.71
    вить
    0.71
    chars
    0.70
     provincias
    0.70
     caule
    0.69
     caracteres
    0.68
    POSITIVE LOGITS
    يل
    0.82
     malnourished
    0.74
    ю
    0.69
    Tool
    0.64
     impaired
    0.64
    神器
    0.64
    يب
    0.63
    ০০০
    0.63
    able
    0.63
    شي
    0.62
    Activations Density 0.001%

    No Known Activations