© 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. 7603
    Prev
    Next
    INDEX
    Explanations

    code comments and separators

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

    The neuron activates on standalone numeric literals (integers or floating-point numbers) in code or comments.

    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
     also
    -2.09
     other
    -1.91
     Also
    -1.75
    Also
    -1.67
    Other
    -1.64
     only
    -1.58
     همچنین
    -1.53
     more
    -1.50
     також
    -1.47
    To
    -1.45
    POSITIVE LOGITS
    ’，
    1.41
    俨
    1.34
    隂
    1.28
    にします
    1.27
     они
    1.27
    ㈬
    1.25
     opérateur
    1.25
     they
    1.24
     boîtier
    1.23
     их
    1.23
    Activations Density 0.129%

    No Known Activations