© 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. 11285
    Prev
    Next
    INDEX
    Explanations

    names of languages

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

    The main thing this neuron does is find mentions of natural language names (e.g. English, French, German, etc.).

    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
     a
    -1.56
    1
    -1.30
     veckor
    -1.28
     verá
    -1.27
     new
    -1.22
     are
    -1.22
     große
    -1.19
     verläng
    -1.18
    5
    -1.16
    <h2>
    -1.16
    POSITIVE LOGITS
    女
    1.32
     núm
    1.31
     imagenes
    1.29
    狁
    1.29
     フロア
    1.27
    ꪔ
    1.24
     atencion
    1.23
     iconos
    1.22
    Прият
    1.21
    
    1.20
    Activations Density 0.038%

    No Known Activations