© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10841
    Prev
    Next
    INDEX
    Explanations

    code and technical terms

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

    comments in code that describe variables, constants, or configuration settings.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    -1.26
     مشکی
    -1.16
    任何
    -1.16
    了我
    -1.13
     same
    -1.11
     what
    -1.09
    wants
    -1.08
    highlights
    -1.07
    YOUR
    -1.06
     quiser
    -1.06
    POSITIVE LOGITS
    chläge
    1.66
     for
    1.51
     to
    1.51
    しておく
    1.46
    metery
    1.41
     goTo
    1.41
     parseFrom
    1.40
     setPrice
    1.38
    olische
    1.35
     "..\..\..\
    1.33
    Activations Density 0.042%

    No Known Activations