© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2229
    Prev
    Next
    INDEX
    Explanations

    narrative structure analysis

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

    The neuron fires strongly on the determiner “those.”

    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
    z
    0.99
    om
    0.89
    ing
    0.83
    OS
    0.79
     muslim
    0.79
    PI
    0.76
    Pi
    0.76
    uk
    0.75
     Gli
    0.75
    j
    0.75
    POSITIVE LOGITS
     configuración
    0.86
     configuração
    0.70
     कनेक्टिविटी
    0.68
     Boley
    0.68
     कॉलेजों
    0.67
     structurally
    0.66
     encontrados
    0.66
     classifies
    0.66
     ژان
    0.66
     بطور
    0.64
    Activations Density 0.000%

    No Known Activations