© 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. 126680
    Prev
    Next
    INDEX
    Explanations

    school and child education

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

    functional components, specifies, SaaS, demonstrating

    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
     gasp
    0.49
     I
    0.49
     post
    0.48
    post
    0.47
     in
    0.46
    ced
    0.46
    listing
    0.46
     ced
    0.46
     individual
    0.45
    cing
    0.45
    POSITIVE LOGITS
     पाठशाला
    0.56
     renderEncoder
    0.52
    粨
    0.51
    授業
    0.50
     গুণ
    0.48
    elje
    0.48
    荠
    0.48
    尟
    0.48
     স্কুলের
    0.47
    児
    0.46
    Activations Density 0.003%

    No Known Activations