© 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. 22-GEMMASCOPE-RES-131K
    7. 72947
    Prev
    Next
    INDEX
    Explanations

    `@param`, `/* comment`, `Q:`, `1.`

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

    The neuron strongly responds to JSDoc‐style comment markup (e.g. leading asterisks, “@” tags, braces and keywords like “param”/“return”).

    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
     réglable
    -1.09
    ﱠ
    -1.07
     keuntungan
    -1.07
     КУ
    -1.05
     Mientras
    -1.05
    +=(
    -1.02
    殤
    -1.01
     діа
    -0.99
    itados
    -0.98
    Mientras
    -0.98
    POSITIVE LOGITS
    ’
    1.15
    oluciones
    1.07
    是一位
    0.99
     to
    0.94
     levit
    0.94
    是一
    0.92
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.92
     amerikanischen
    0.90
     Vertrieb
    0.89
    tische
    0.88
    Activations Density 0.002%

    No Known Activations