© 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. 40-GEMMASCOPE-2-RES-262K
    7. 214703
    Prev
    Next
    INDEX
    Explanations

    current news rundown

    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_40_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
     interviewing
    0.50
    ധ
    0.47
    проек
    0.45
     interrogated
    0.43
     classifying
    0.43
     shelved
    0.39
     plans
    0.39
    项目中
    0.39
     determining
    0.38
    ≔
    0.38
    POSITIVE LOGITS
     Recap
    0.95
     recap
    0.95
     summary
    0.86
     weekly
    0.82
     Summary
    0.82
     Weekly
    0.82
    summary
    0.80
     daily
    0.76
    Weekly
    0.75
     roundup
    0.75
    Activations Density 0.037%

    No Known Activations