© 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. 41134
    Prev
    Next
    INDEX
    Explanations

    AngularJS directives and scope

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     so
    -1.59
     from
    -1.59
     most
    -1.53
     this
    -1.46
     Kartoffeln
    -1.44
    دت
    -1.38
     then
    -1.37
     up
    -1.33
     current
    -1.32
     best
    -1.31
    POSITIVE LOGITS
    "]=
    1.45
     și
    1.38
    Hô
    1.27
    ørte
    1.27
     atrak
    1.26
     confirmar
    1.25
     recev
    1.25
    kijk
    1.24
    гина
    1.23
    voer
    1.23
    Activations Density 0.022%

    No Known Activations