© 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. 6454
    Prev
    Next
    INDEX
    Explanations

    context before lists or questions

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

    This neuron fires strongly on the last substantive word before a sentence or section break.

    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
    J
    0.28
    greater
    0.24
    将其
    0.24
    T
    0.24
    ב
    0.24
    U
    0.24
    p
    0.23
    im
    0.23
    ہائی
    0.22
    $",
    0.22
    POSITIVE LOGITS
     अधिकतर
    0.29
     Films
    0.29
     cioè
    0.28
     Solids
    0.28
     But
    0.28
     hehe
    0.28
     Anyway
    0.27
     anyway
    0.27
     oscillators
    0.27
     calendario
    0.27
    Activations Density 0.000%

    No Known Activations