© 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. 61362
    Prev
    Next
    INDEX
    Explanations

    classified or evaluated

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

    The neuron activates on the word “considered” (i.e. subjective/evaluative claims marked by “considered”).

    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
    刧
    -2.20
     autre
    -1.88
    ufige
    -1.84
    搗
    -1.75
    ￬
    -1.72
    else
    -1.71
    BuilderFactory
    -1.69
     they
    -1.67
    为了
    -1.65
    WARDS
    -1.64
    POSITIVE LOGITS
    '
    2.67
     a
    2.66
    ’
    2.19
    ,“
    2.14
     parecía
    1.71
     trovano
    1.62
     Eigentum
    1.59
    
    1.59
    .“
    1.54
    :“
    1.48
    Activations Density 0.019%

    No Known Activations