© 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. 22-GEMMASCOPE-RES-131K
    7. 34702
    Prev
    Next
    INDEX
    Explanations

    comfort and support

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

    The main thing this neuron does is detect descriptions of ergonomic support or comfort surfaces (e.g., grips, pads, and cushioning designed to provide comfort or 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_22/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
    וֹ
    -1.57
    וּ
    -1.52
     чехол
    -1.35
     бампер
    -1.35
    ּוֹ
    -1.31
    ֶּ
    -1.30
    ִּ
    -1.29
     monetary
    -1.21
     المسؤول
    -1.21
    があれば
    -1.20
    POSITIVE LOGITS
    ׇ
    1.55
    comfortable
    1.45
    ussch
    1.43
     kialak
    1.33
    Comfortable
    1.23
     comfortable
    1.17
     ܐ
    1.16
    Comfort
    1.16
     userSchema
    1.16
     comfort
    1.14
    Activations Density 0.065%

    No Known Activations