© 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. 50141
    Prev
    Next
    INDEX
    Explanations

    comfort and discomfort

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

    This neuron fires on words and word pieces that convey comfort, ease, or a state of being at ease.

    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
    Respondent
    -0.79
    Nelson
    -0.73
    hoku
    -0.73
     diadakan
    -0.73
    clair
    -0.73
    sap
    -0.71
    ❥
    -0.71
    arb
    -0.70
     prévoir
    -0.70
     Telangana
    -0.69
    POSITIVE LOGITS
     comfortable
    6.13
    comfortable
    4.69
     Comfortable
    4.59
    Comfortable
    4.47
     comfy
    4.06
     uncomfortable
    4.06
     comfort
    3.81
     комфор
    3.67
     COMFORT
    3.61
     comfor
    3.53
    Activations Density 0.066%

    No Known Activations