© 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. 10-GEMMASCOPE-RES-131K
    7. 129697
    Prev
    Next
    INDEX
    Explanations

    describing soft qualities

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

    The main thing this neuron does is detect language describing softness or soft texture.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    </strong>
    -2.69
    嘡
    -1.93
     Their
    -1.70
    小镇
    -1.66
    ない
    -1.66
     
    -1.61
     vanden
    -1.60
    ош
    -1.56
    皷
    -1.53
    鈈
    -1.53
    POSITIVE LOGITS
    9
    2.63
    7
    2.61
    1
    2.53
    6
    2.38
    3
    2.34
    4
    2.27
    5
    2.27
    ;
    2.19
    8
    2.11
    We
    2.02
    Activations Density 0.019%

    No Known Activations