© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59580
    Prev
    Next
    INDEX
    Explanations

    included, excluded, considered

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

    The neuron activates on numeric data and statistical values (e.g. sample sizes, percentages, measurements) 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
    gendes
    -1.09
    Selama
    -0.96
     теперь
    -0.96
     diputados
    -0.94
    μαι
    -0.93
    matching
    -0.92
    Açık
    -0.92
    
    -0.91
    Ende
    -0.90
     подобрать
    -0.90
    POSITIVE LOGITS
     this
    1.38
     as
    1.25
     encantado
    1.20
    )))))
    1.18
     then
    1.16
     these
    1.13
    ただし
    1.13
    😹
    1.12
     tohto
    1.10
     asmen
    1.10
    Activations Density 0.092%

    No Known Activations