© 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. 214172
    Prev
    Next
    INDEX
    Explanations

    diseases and conditions

    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
    水の
    0.41
    ckiego
    0.39
     иска
    0.39
     huv
    0.38
    خدام
    0.37
    ணய
    0.37
    NAVIGATION
    0.37
    鋯
    0.37
    आप
    0.36
    potion
    0.36
    POSITIVE LOGITS
    barS
    0.49
    acam
    0.42
    bar
    0.41
     Stoff
    0.41
     মাঝারি
    0.40
     Business
    0.40
     Bar
    0.40
    uje
    0.40
     acad
    0.39
    淮
    0.39
    Activations Density 0.000%

    No Known Activations