© 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. 31-GEMMASCOPE-2-RES-16K
    7. 1873
    Prev
    Next
    INDEX
    Explanations

    ending punctuation

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

    The neuron fires most strongly on long, continuous blocks of text (i.e. lengthy paragraphs).

    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_31_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
    (!)
    0.82
    (?)
    0.70
    ̀
    0.64
    씐
    0.64
    뚠
    0.63
    <s>
    0.62
    (?
    0.61
     যেকোন
    0.61
     kì
    0.61
    怼
    0.61
    POSITIVE LOGITS
     ..."
    1.07
     •
    0.92
     例文帳に追加
    0.91
     http
    0.91
    ĭ
    0.90
    Ĭ
    0.89
    Ī
    0.88
     ©
    0.87
     しかし
    0.87
    ."—
    0.86
    Activations Density 2.088%

    No Known Activations