© 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. 23864
    Prev
    Next
    INDEX
    Explanations

    technical questions and code snippets

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

    The neuron fires on code identifier tokens that represent constant names (e.g. error or flag constants written in ALL‐CAPS or CamelCase).

    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
    蕯
    -2.34
    注意事
    -2.14
     are
    -2.13
     orologio
    -2.02
    ⒋
    -2.00
     semarang
    -1.95
     problemi
    -1.92
     borsa
    -1.92
    iſter
    -1.91
    おはようございます
    -1.90
    POSITIVE LOGITS
     “
    2.34
     -
    2.23
    ing
    2.20
    я
    2.19
    ’
    2.11
     "
    2.09
    </h2>
    1.88
    </strong>
    1.81
    </h3>
    1.75
     else
    1.74
    Activations Density 0.000%

    No Known Activations