© 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. 21909
    Prev
    Next
    INDEX
    Explanations

    fundamental education concepts

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

    royal navy

    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
     molecules
    0.47
     immaterial
    0.46
     gaseous
    0.42
     ambulances
    0.42
     dioxygen
    0.42
    炼
    0.42
    的气
    0.41
    钾
    0.41
    卟
    0.41
    气
    0.41
    POSITIVE LOGITS
     Schwerpunkt
    0.50
    UR
    0.47
     \{
    0.47
    EDUCATION
    0.47
    EDUC
    0.47
    fundamental
    0.47
    Bew
    0.45
    Fundamental
    0.45
    Fundamentals
    0.45
    EIS
    0.45
    Activations Density 0.000%

    No Known Activations