© 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. 14760
    Prev
    Next
    INDEX
    Explanations

    listing

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

    This neuron is highly activated by sentence-ending punctuation (periods and exclamation points).

    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
    अभ
    0.59
    saxophone
    0.57
     yawning
    0.56
     můžete
    0.55
    paration
    0.54
     पॉप
    0.54
    পণ
    0.54
    빛
    0.54
     quietly
    0.53
    ="
    0.53
    POSITIVE LOGITS
     According
    0.71
     이동
    0.64
     메소
    0.63
    ၡ
    0.62
     ตาม
    0.61
     利用
    0.61
     Interestingly
    0.61
    |।
    0.59
     Menurut
    0.59
     '/',
    0.59
    Activations Density 0.000%

    No Known Activations