© 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. 37999
    Prev
    Next
    INDEX
    Explanations

    overwhelming community support

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

    This neuron detects words and phrases that signal collective support or solidarity (e.g. “solidarity,” “support,” “outpouring of support,” “community support”).

    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
    れば
    -0.85
    mListener
    -0.83
    ęcie
    -0.78
    эк
    -0.76
    дые
    -0.75
    ree
    -0.74
    yay
    -0.73
    매
    -0.72
    嘉宾
    -0.72
    sigma
    -0.72
    POSITIVE LOGITS
     support
    2.30
     out
    1.82
     overwhelming
    1.80
    support
    1.63
     response
    1.62
     community
    1.61
     generosity
    1.56
     messages
    1.55
    Support
    1.55
     responses
    1.50
    Activations Density 0.022%

    No Known Activations