© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13418
    Prev
    Next
    INDEX
    Explanations

    package declarations

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

    The neuron fires on punctuation delimiters in source code—especially dots (“.”) and semicolons (“;”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     their
    -1.02
     регулярно
    -0.99
    urnum
    -0.94
    onuc
    -0.93
    athons
    -0.92
    ūnas
    -0.91
    ogues
    -0.90
    迸
    -0.90
    ׳
    -0.90
    preneur
    -0.90
    POSITIVE LOGITS
     example
    1.43
     examples
    1.30
     první
    1.21
     first
    1.17
     teljes
    1.11
    فقط
    1.11
     przykład
    1.10
    Вариант
    1.06
    Example
    1.06
    我が家の
    1.05
    Activations Density 0.015%

    No Known Activations