© 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. 57308
    Prev
    Next
    INDEX
    Explanations

    Home, Furniture, DIY, Motors, Apparel

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

    skills classification ESCO categories

    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
     &
    0.49
     Rocks
    0.45
     Attractions
    0.44
     &,
    0.43
    ographics
    0.42
     Lore
    0.41
    \\\
    0.40
     กราบ
    0.39
    ☆
    0.38
    &#
    0.37
    POSITIVE LOGITS
     carácter
    0.51
    monitoring
    0.51
     öğrenc
    0.50
    quantum
    0.50
     szkoły
    0.49
    students
    0.48
    semester
    0.48
    stud
    0.47
    definition
    0.46
     economists
    0.46
    Activations Density 0.001%

    No Known Activations