© 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. 104160
    Prev
    Next
    INDEX
    Explanations

    questions and names

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

    The neuron fires on numeric literals and digits (e.g. numbers and numeric tokens) embedded in code or 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
     and
    -1.72
     baterías
    -1.57
    KIDS
    -1.54
    
    -1.52
     cantidades
    -1.52
    
    -1.50
    曏
    -1.49
     electricidad
    -1.48
    SONY
    -1.47
     minerales
    -1.42
    POSITIVE LOGITS
     of
    2.36
    6
    1.99
     he
    1.81
    2
    1.76
    исправ
    1.72
    沨
    1.66
    7
    1.66
     untuk
    1.60
    5
    1.52
    逦
    1.52
    Activations Density 0.000%

    No Known Activations