© 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. 85261
    Prev
    Next
    INDEX
    Explanations

    medical and biological terms

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

    non-text elements like special Unicode characters or formatting codes that appear at the end of content blocks.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is strongly activated by invisible or special (non-standard/zero-width) punctuation characters (e.g. BOM or non-breaking space markers).

    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
     persönlichen
    -1.76
     richtigen
    -1.63
     eigentliche
    -1.61
     notwendigen
    -1.59
     besonderen
    -1.59
     its
    -1.59
     sicheren
    -1.58
     großartige
    -1.57
     wichtigen
    -1.55
     Absicht
    -1.55
    POSITIVE LOGITS
    SE
    1.43
    C
    1.38
     bewer
    1.34
     appels
    1.30
    然后再
    1.29
    basically
    1.27
     couverts
    1.23
     vertes
    1.22
     standout
    1.20
     تصوير
    1.20
    Activations Density 0.016%

    No Known Activations