© 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. 9645
    Prev
    Next
    INDEX
    Explanations

    game-based curriculum

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

    The neuron responds to the very first content word at the start of a 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
     sıvı
    0.84
    νά
    0.80
    Ź
    0.80
    onnés
    0.80
    czyć
    0.80
     बाब
    0.79
    ໊
    0.79
    ாய
    0.78
    ליו
    0.78
    ակի
    0.77
    POSITIVE LOGITS
    es
    0.77
    d
    0.70
     Ingle
    0.68
     antics
    0.67
    半島
    0.67
     tattoos
    0.67
    ция
    0.65
     moſt
    0.64
     WHAT
    0.64
     whats
    0.63
    Activations Density 0.000%

    No Known Activations