© 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-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 1973
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    és
    0.97
    w
    0.96
    ม
    0.92
    ა
    0.87
    人
    0.81
    ríklad
    0.80
     that
    0.78
    ř
    0.78
    ர்
    0.76
    that
    0.75
    POSITIVE LOGITS
     on
    0.95
    ב
    0.94
     to
    0.93
    ל
    0.88
    ור
    0.88
    ید
    0.87
    ע
    0.87
    ൂ
    0.85
    έ
    0.80
    க்கு
    0.79
    Activations Density 0.938%

    No Known Activations