© 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. 22-GEMMASCOPE-RES-131K
    7. 54131
    Prev
    Next
    INDEX
    Explanations

    Q: followed by other tokens

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

    This neuron fires on comment‐block markup and metadata tokens (e.g. leading asterisks, @ annotations, “--” or “---” lines) used in code comments and doc headers.

    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
     Puedes
    -1.41
     vulgaires
    -1.24
     Otras
    -1.19
    -1.19
     Pueden
    -1.16
    -1.15
    cestry
    -1.14
     Puede
    -1.14
    -1.13
    oyer
    -1.12
    POSITIVE LOGITS
    ↵↵
    1.20
     &
    1.12
     and
    1.12
     <
    1.12
     ‘
    1.09
    包含
    1.01
    有一
    1.00
    //
    0.98
    h
    0.98
    \
    0.98
    Activations Density 0.009%

    No Known Activations