© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 104615
    Prev
    Next
    INDEX
    Explanations

    special characters in code/templates

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

    special characters and symbols used in technical, mathematical, or markup contexts (like `#`, `$`, `~`, `^`, `\`, parentheses in code/formulas).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on isolated special‐purpose punctuation tokens—particularly markup/math symbols such as “#”, “$”, and “~”.

    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
     an
    -2.05
    genicity
    -1.85
     a
    -1.76
     because
    -1.74
     has
    -1.65
    濯
    -1.65
     gracioso
    -1.58
    ícias
    -1.52
     llorar
    -1.50
     since
    -1.48
    POSITIVE LOGITS
    ↵
    1.67
     intrigu
    1.62
    3
    1.55
     всех
    1.55
    4
    1.52
    });
    1.52
     surpris
    1.51
    <td>
    1.48
     omin
    1.48
     "..
    1.46
    Activations Density 0.118%

    No Known Activations