© 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. 34-GEMMASCOPE-RES-131K
    7. 77527
    Prev
    Next
    INDEX
    Explanations

    punctuations and separators

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

    The neuron strongly activates on numeric or indexing tokens (e.g. section/list numbers) and URL‐related tokens (e.g. “http”, “https”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     without
    -1.07
     so
    -0.93
     to
    -0.88
     will
    -0.85
     for
    -0.82
    -
    -0.81
     should
    -0.81
     profound
    -0.78
     noticeably
    -0.75
     as
    -0.73
    POSITIVE LOGITS
    、
    1.65
    。
    1.48
    ；
    1.25
    ،
    1.23
    ）。
    1.16
    ，
    1.14
    ：
    1.14
    ।
    1.05
    ）
    1.02
    ؛
    1.02
    Activations Density 0.024%

    No Known Activations