© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 65470
    Prev
    Next
    INDEX
    Explanations

    political parties, religions, or national groups

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

    The neuron detects numeric tokens, especially years, election vote counts or percentages, and other numerical data.

    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
     ancak
    -1.47
     that
    -1.38
    (){
    -1.36
    ()");
    -1.30
     $=$
    -1.29
    任何
    -1.27
    actéristiques
    -1.26
    filé
    -1.26
     for
    -1.25
     ۱۴
    -1.24
    POSITIVE LOGITS
     it
    1.58
     here
    1.55
    .
    1.41
    there
    1.35
     at
    1.33
    這裡
    1.26
     and
    1.26
     there
    1.25
     in
    1.23
     тук
    1.17
    Activations Density 0.245%

    No Known Activations