© 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. 39420
    Prev
    Next
    INDEX
    Explanations

    a followed by a concept

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

    The neuron fires on numeric tokens—Arabic numerals and numeric values (including integers and decimals)—whenever they appear in the text.

    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
    ют
    -1.59
     ""),
    -1.45
    "}";
    -1.44
    ursos
    -1.38
    ursday
    -1.35
     "";
    
    -1.33
    SizeF
    -1.31
    }());
    -1.30
     to
    -1.30
     a
    -1.30
    POSITIVE LOGITS
     також
    1.67
     only
    1.56
     costuras
    1.47
     needed
    1.46
     fisuras
    1.43
     time
    1.39
     baterías
    1.38
     often
    1.37
     importado
    1.35
     telefónica
    1.35
    Activations Density 0.106%

    No Known Activations