© 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. 34-GEMMASCOPE-RES-131K
    7. 64310
    Prev
    Next
    INDEX
    Explanations

    going out or staying in

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

    The neuron fires on words and phrases describing situations or conditions that prevent or strongly discourage people from going outdoors or carrying out normal activities.

    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
    ftet
    -0.79
    नीय
    -0.79
    ariki
    -0.76
    ghest
    -0.75
    nacht
    -0.75
    ሓ
    -0.74
    佬
    -0.73
    quía
    -0.72
     Arrival
    -0.72
     Invasion
    -0.71
    POSITIVE LOGITS
     venture
    3.56
     venturing
    3.34
     ventured
    3.09
     ventures
    2.66
     Venture
    2.42
    venture
    2.31
     outside
    2.30
     out
    2.28
     keluar
    2.25
     outings
    2.25
    Activations Density 0.077%

    No Known Activations