© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 90750
    Prev
    Next
    INDEX
    Explanations

    rib-knit cuff

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

    covered in

    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
    Negative Logits
     gagal
    0.46
    дения
    0.45
     ciudadanos
    0.43
     محس
    0.41
     getDateTime
    0.40
     permitem
    0.40
     பயன
    0.40
    и
    0.40
     considerare
    0.40
     تنها
    0.40
    POSITIVE LOGITS
    μί
    0.49
    lx
    0.48
     Série
    0.48
    circle
    0.47
     Shirt
    0.47
    zón
    0.46
     XII
    0.46
    ξύ
    0.46
    isPartOf
    0.45
     Ornament
    0.45
    Activations Density 0.001%

    No Known Activations