© 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. 26550
    Prev
    Next
    INDEX
    Explanations

    cuisines and food types

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

    atmosphere and service

    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
     божомолдору
    0.43
     matchups
    0.39
     отношению
    0.38
    लिब्र
    0.38
    鞣
    0.38
    LIGHT
    0.37
     preponderance
    0.37
     dereg
    0.37
    刃
    0.37
     능력
    0.37
    POSITIVE LOGITS
     Turning
    0.54
    ícím
    0.44
     word
    0.40
    Turning
    0.39
     Remark
    0.39
    goed
    0.39
     turning
    0.39
    🍧
    0.39
     Fountain
    0.39
     remarquer
    0.38
    Activations Density 0.001%

    No Known Activations