© 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. 105137
    Prev
    Next
    INDEX
    Explanations

    names, music terms, and specific words

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

    The neuron fires on content-bearing nouns and names—especially uncommon proper nouns and technical terms.

    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
    菔
    -2.41
     wollten
    -2.39
     mussten
    -2.38
    ünstler
    -2.33
    >
    -2.33
    ",
    -2.30
    n
    -2.27
    
    -2.27
     nahmen
    -2.25
    垍
    -2.25
    POSITIVE LOGITS
     различ
    2.30
     разнообраз
    2.28
    至此
    2.16
     It
    2.16
    缃
    2.14
    驺
    2.14
    .
    2.09
     Then
    2.08
     Also
    2.03
     fragmented
    2.03
    Activations Density 0.010%

    No Known Activations