© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71347
    Prev
    Next
    INDEX
    Explanations

    programming keywords and delimiters

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

    The neuron detects numeric literal tokens (integer or floating‐point constants) in code.

    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
     this
    -2.91
     from
    -2.63
     with
    -2.59
     in
    -2.52
     one
    -2.34
    There
    -2.30
     two
    -2.30
    Even
    -2.28
    After
    -2.27
     and
    -2.23
    POSITIVE LOGITS
    赑
    2.47
     semelh
    2.44
     juſt
    2.41
    ܊
    2.38
     unſ
    2.33
     leſs
    2.19
    ໊
    2.06
     REALLY
    2.05
    鲩
    2.05
     และ
    2.02
    Activations Density 0.032%

    No Known Activations