© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11085
    Prev
    Next
    INDEX
    Explanations

    concept of illness

    np_acts-logits-general · gemini-2.5-flash-lite

    unresolved resolution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ”
    0.43
    ”,
    0.40
    ”.
    0.38
    ”—
    0.36
    > </
    0.35
     talked
    0.34
    rdquo
    0.34
     noodle
    0.34
     জেনে
    0.34
     “”
    0.34
    POSITIVE LOGITS
     захворю
    0.43
     gubit
    0.39
     doenças
    0.38
     Erkrank
    0.37
     bactéries
    0.37
     erricht
    0.36
     malattie
    0.36
     lluvias
    0.36
    Он
    0.35
     닮
    0.35
    Activations Density 1.180%

    No Known Activations