© 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. 2475
    Prev
    Next
    INDEX
    Explanations

    end of lists etc

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    지와
    0.59
    ແລະ
    0.57
     fă
    0.54
    ö
    0.54
     особен
    0.52
    බා
    0.51
    ดวก
    0.50
     certe
    0.50
     இரண்டு
    0.49
     ਅਤੇ
    0.49
    POSITIVE LOGITS
    c
    0.61
    ri
    0.57
     is
    0.55
    ch
    0.53
    tr
    0.50
    п
    0.50
    kt
    0.49
    OS
    0.49
    ني
    0.49
    th
    0.49
    Activations Density 0.288%

    No Known Activations