© 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. 42700
    Prev
    Next
    INDEX
    Explanations

    foreign proper nouns and technical terms

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

    This neuron selectively fires on capitalized named-entity tokens (proper names of places or people).

    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
    屣
    -2.91
     It
    -2.55
    Odpovědět
    -2.41
     desempen
    -2.31
    莇
    -2.27
     televisão
    -2.22
     طويلة
    -2.22
    蜮
    -2.22
    ן
    -2.20
    actéristi
    -2.17
    POSITIVE LOGITS
     is
    3.47
    ar
    2.66
    </h4>
    2.36
    p
    2.27
    ttemberg
    2.27
    aran
    2.20
     например
    2.19
    先に
    2.17
     adjective
    2.17
    of
    2.16
    Activations Density 0.002%

    No Known Activations