© 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. 10-GEMMASCOPE-RES-131K
    7. 87095
    Prev
    Next
    INDEX
    Explanations

    code comments /**

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

    The neuron fires on the opening delimiters of multi-line or documentation comments in source code (e.g. “/*” or “/**”).

    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
    0
    -2.33
    8
    -2.25
    4
    -2.23
    6
    -2.13
    2
    -2.05
    7
    -1.91
    9
    -1.89
    1
    -1.82
    3
    -1.72
    in
    -1.71
    POSITIVE LOGITS
     have
    1.80
     when
    1.69
    靫
    1.67
    
    1.53
    فره
    1.52
    炻
    1.49
    饧
    1.48
    簠
    1.48
    🢒
    1.46
    chica
    1.41
    Activations Density 0.008%

    No Known Activations