© 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-16K
    7. 8317
    Prev
    Next
    INDEX
    Explanations

    clear and decreased medical terms

    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_16k_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
    brush
    0.40
    Aggregation
    0.38
    پیش
    0.37
    Ten
    0.37
    Raising
    0.37
    溦
    0.37
    торое
    0.36
     ferrugineux
    0.36
    Preparing
    0.36
    辊
    0.36
    POSITIVE LOGITS
     extras
    0.42
     Extras
    0.42
     Extra
    0.41
     Ama
    0.41
     RSC
    0.40
    ້າ
    0.40
    extras
    0.40
     extra
    0.39
    extra
    0.38
     Listen
    0.38
    Activations Density 0.039%

    No Known Activations