© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 4643
    Prev
    Next
    INDEX
    Explanations

    fabric and cloth

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

    fabric and cloth

    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_53_width_65k_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
     пенсион
    0.50
    跷
    0.47
     pensions
    0.47
     neuropsych
    0.45
     गैंगस्टर
    0.43
     Pensions
    0.42
    蝸
    0.42
     пое
    0.41
     кеңсесинде
    0.40
    _{-}\
    0.40
    POSITIVE LOGITS
     fabrics
    3.66
     fabric
    3.61
     cloth
    3.52
     Fabrics
    3.23
     Cloth
    3.13
     Fabric
    3.11
     ткань
    3.11
    fabric
    3.09
     vải
    3.08
     ткани
    3.05
    Activations Density 0.274%

    No Known Activations