© 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-262K
    7. 34364
    Prev
    Next
    INDEX
    Explanations

    arrangement of leaves

    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_262k_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
     الحي
    0.60
    الي
    0.58
    柇
    0.57
     சூரிய
    0.52
    乑
    0.52
    colare
    0.52
     ಘ
    0.51
     အ
    0.51
     적용
    0.50
    리가
    0.50
    POSITIVE LOGITS
     sail
    0.55
     weed
    0.53
     dare
    0.52
    <0xBF>
    0.52
     rocket
    0.52
    エット
    0.52
     pyro
    0.51
     prominence
    0.51
     isset
    0.50
     overthrow
    0.50
    Activations Density 0.009%

    No Known Activations