© 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-65K
    7. 3605
    Prev
    Next
    INDEX
    Explanations

    history of present illness

    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_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
    ację
    0.38
    треб
    0.38
    ológ
    0.35
    <\/
    0.35
    ونة
    0.34
    ohner
    0.34
     технику
    0.34
    <div>
    0.33
    ෙක්
    0.33
    本项目
    0.33
    POSITIVE LOGITS
     tvam
    0.44
     lze
    0.43
     svih
    0.43
    ματος
    0.42
     fattori
    0.41
     lineages
    0.40
     fatores
    0.40
    liness
    0.39
     finns
    0.38
     將
    0.38
    Activations Density 0.065%

    No Known Activations