© 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. 34-GEMMASCOPE-RES-131K
    7. 66294
    Prev
    Next
    INDEX
    Explanations

    demands for change or justice

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

    The neuron detects words expressing calls to action or collective demands (e.g. “demanding,” “encouraging,” “calling for,” “rally for”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     khuyến
    -1.13
     []:
    -1.04
     might
    -1.00
     offer
    -0.96
    REQUEST
    -0.93
    cón
    -0.90
     may
    -0.90
     grossesse
    -0.88
     possibly
    -0.87
     will
    -0.86
    POSITIVE LOGITS
     better
    1.66
     more
    1.38
     changes
    1.33
     greater
    1.33
     более
    1.27
     improvements
    1.27
    greater
    1.27
    changes
    1.23
    更多的
    1.23
    更好的
    1.22
    Activations Density 0.047%

    No Known Activations