© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69775
    Prev
    Next
    INDEX
    Explanations

    thenthatlikeEven

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

    The neuron is looking for sentence-ending punctuation (runs of dots, question marks, or exclamation points).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     to
    -2.05
     Internasional
    -2.02
     memperoleh
    -1.95
    انظر
    -1.74
    ଵ
    -1.72
    増加
    -1.71
    ďaka
    -1.70
    ervare
    -1.69
     diadakan
    -1.69
     by
    -1.68
    POSITIVE LOGITS
     then
    2.38
    骉
    2.36
     that
    2.03
    ⽼
    2.02
     like
    1.88
    埽
    1.88
    那个
    1.83
    ⾞
    1.78
     leher
    1.77
    miot
    1.70
    Activations Density 0.294%

    No Known Activations