© 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. 40007
    Prev
    Next
    INDEX
    Explanations

    static keyword in code

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

    The neuron fires on integer literal tokens (numbers) in the 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_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
    过头
    -1.44
    อื่น
    -1.40
    но
    -1.35
    🫴
    -1.35
    kym
    -1.32
    蛱
    -1.31
     constitué
    -1.30
     véritables
    -1.30
     Tienes
    -1.30
    栒
    -1.30
    POSITIVE LOGITS
    For
    1.83
    {
    1.77
    "
    1.73
    It
    1.70
    )
    1.67
    On
    1.63
    -
    1.61
    '
    1.58
    }
    1.53
    With
    1.52
    Activations Density 0.002%

    No Known Activations