© 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. 22-GEMMASCOPE-RES-131K
    7. 35445
    Prev
    Next
    INDEX
    Explanations

    file paths and code separators

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

    This neuron detects numeric literals (integers or floats) in the text.

    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
    kenal
    -1.38
     and
    -1.33
    来週
    -1.28
     arreg
    -1.23
     потім
    -1.23
    Tarifs
    -1.21
    今朝
    -1.21
    If
    -1.20
     embrague
    -1.20
    感じで
    -1.16
    POSITIVE LOGITS
    an
    1.41
     is
    1.27
    n
    1.25
    la
    1.24
    ca
    1.22
     ''
    1.20
    遑
    1.20
    le
    1.20
    w
    1.20
    ⨯
    1.19
    Activations Density 0.107%

    No Known Activations