© 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. 57359
    Prev
    Next
    INDEX
    Explanations

    cotton and wool fibers

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

    terminology and materials related to textiles, fabrics, and fibers.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    ตล
    -0.69
    ناق
    -0.66
    praise
    -0.65
     принципе
    -0.65
    Costa
    -0.64
    înes
    -0.63
     CONTR
    -0.63
    悖
    -0.63
    凪
    -0.63
     추
    -0.63
    POSITIVE LOGITS
     cotton
    2.05
    cotton
    1.63
     wool
    1.59
     fibre
    1.58
     fiber
    1.58
     fibrous
    1.49
    Cotton
    1.48
     Fibre
    1.47
     Cotton
    1.41
    wool
    1.40
    Activations Density 0.047%

    No Known Activations