© 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. 87083
    Prev
    Next
    INDEX
    Explanations

    like

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

    This neuron responds to punctuation and other structural markers—commas, colons, dashes, quotation marks, parentheses, etc.—that set off clauses or asides.

    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
     and
    -2.19
    ન
    -1.17
     vijf
    -1.14
     She
    -1.13
     öst
    -1.13
     so
    -1.12
    Vikt
    -1.10
     bölüm
    -1.09
     път
    -1.09
     große
    -1.07
    POSITIVE LOGITS
     alimenti
    1.78
     jurídica
    1.57
    like
    1.56
     psicológica
    1.54
     ähnlichen
    1.45
     educativa
    1.44
     científica
    1.43
     geringen
    1.42
     only
    1.41
    あなたが
    1.41
    Activations Density 0.048%

    No Known Activations