© 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. 112072
    Prev
    Next
    INDEX
    Explanations

    planned activities

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

    The neuron activates on mentions of “activity” (and its plural “activities”) 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
    '
    -1.71
    ’
    -1.55
    璈
    -1.45
    hasta
    -1.37
     upwards
    -1.36
     بعض
    -1.34
     provocó
    -1.34
    
    -1.34
    醅
    -1.33
     tocó
    -1.30
    POSITIVE LOGITS
    翃
    1.66
     hijas
    1.55
    元々
    1.53
    地区的
    1.51
    __':
    1.48
     demonios
    1.45
    ٨
    1.43
     doulou
    1.41
     cuarent
    1.41
     peores
    1.40
    Activations Density 0.035%

    No Known Activations