© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 181324
    Prev
    Next
    INDEX
    Explanations

    diabetes mellitus

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

    drying immediately, prints for every pair, differences between

    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_31_width_262k_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
    ᱭ
    0.46
     প্রকৃতপক্ষে
    0.45
    農
    0.44
    申請
    0.44
    麥
    0.44
    財布
    0.43
    不在
    0.43
    購
    0.43
    いない
    0.42
    わからない
    0.42
    POSITIVE LOGITS
    രക്ഷ
    0.48
     estilos
    0.46
    ideos
    0.45
     flares
    0.45
    orten
    0.44
     చెందిన
    0.44
     flair
    0.44
     Ontology
    0.44
    莪
    0.44
     Styles
    0.43
    Activations Density 0.001%

    No Known Activations