© 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. 13330
    Prev
    Next
    INDEX
    Explanations

    limerick

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

    The neuron is signaling the ends of sentences—that is, it lights up most strongly on tokens that immediately carry sentence‐final punctuation.

    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
     Enlarg
    0.67
    َق
    0.67
     combine
    0.66
    CS
    0.65
     ép
    0.65
     caméra
    0.64
    न्
    0.63
     ен
    0.63
    WEST
    0.63
     ስለዚህ
    0.61
    POSITIVE LOGITS
    いが
    0.88
    ᕝ
    0.88
    ikale
    0.86
    曳
    0.86
     legumes
    0.84
    বিট
    0.84
     Elig
    0.82
     экономи
    0.81
    ெமி
    0.81
     Э
    0.81
    Activations Density 0.001%

    No Known Activations