© 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. 114862
    Prev
    Next
    INDEX
    Explanations

    materials, technology, production

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

    questions and specific entities

    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
     européen
    0.59
    演讲
    0.51
     espalda
    0.49
    奋
    0.47
     yanlı
    0.47
     друже
    0.46
    地铁
    0.46
     hátsó
    0.45
    游泳
    0.45
     لكرة
    0.44
    POSITIVE LOGITS
     and
    0.57
     C
    0.51
     CaO
    0.51
     P
    0.50
     powders
    0.48
    incorporated
    0.48
     technology
    0.48
     materials
    0.47
     PRODUCTION
    0.46
     tokens
    0.46
    Activations Density 0.001%

    No Known Activations