© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20099
    Prev
    Next
    INDEX
    Explanations

    multiple items or variations

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

    The neuron activates on words expressing large, non‐specific quantities—most strongly on “many.”

    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
    ARON
    -1.62
     furthermore
    -1.55
     gustado
    -1.54
     therefore
    -1.51
     he
    -1.43
    mazing
    -1.40
    ையும்
    -1.40
    
    -1.39
    扨
    -1.38
    ными
    -1.38
    POSITIVE LOGITS
    稣
    1.73
     verschiedenen
    1.68
    дина
    1.59
     acest
    1.58
     different
    1.53
    ໊
    1.48
    ############
    1.47
    皤
    1.46
    𖥧
    1.45
     spécialement
    1.43
    Activations Density 0.031%

    No Known Activations