© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2789
    Prev
    Next
    INDEX
    Explanations

    html tags and attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    اً
    1.96
    ByAppending
    1.87
    性和
    1.80
    S
    1.77
    性が
    1.77
    Ο
    1.77
    ଅ
    1.76
    ًا
    1.71
    دت
    1.70
    パクト
    1.68
    POSITIVE LOGITS
    hopefully
    1.96
     해당
    1.94
    achter
    1.90
     particulares
    1.85
     wij
    1.85
    なんと
    1.83
     Sincerely
    1.82
     lodged
    1.81
     symplectic
    1.77
     nemo
    1.77
    Activations Density 0.112%

    No Known Activations