© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 17128
    Prev
    Next
    INDEX
    Explanations

    carpet and upholstery materials

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

    fabric, leather, upholstery, carpet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    收聽
    0.50
    짓
    0.45
     underdeveloped
    0.45
     বিদ্যুৎ
    0.43
     transcriptional
    0.42
    ร่
    0.42
    ยิน
    0.41
    ICA
    0.41
    ዛ
    0.41
    ጋገ
    0.41
    POSITIVE LOGITS
     upholstery
    0.84
     carpets
    0.77
     carpet
    0.70
    carpet
    0.69
     upholstered
    0.66
     Carpet
    0.63
     uphol
    0.61
    沙发
    0.59
     carpeting
    0.55
     sofa
    0.55
    Activations Density 0.156%

    No Known Activations