© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 101702
    Prev
    Next
    INDEX
    Explanations

    soups and bisques

    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_all/layer_41_width_262k_l0_big
    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
     mammals
    0.43
     স্যা
    0.43
    チュラル
    0.42
    boldsymbol
    0.40
     meat
    0.39
     mā
    0.39
    🍖
    0.39
    iciencia
    0.39
    oggle
    0.38
     mammal
    0.38
    POSITIVE LOGITS
     soup
    1.16
    Soup
    1.04
     Soup
    1.04
    soup
    0.98
     soups
    0.95
    スープ
    0.78
     sopa
    0.68
     bisque
    0.63
    汤
    0.60
     soupe
    0.51
    Activations Density 0.001%

    No Known Activations