© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72313
    Prev
    Next
    INDEX
    Explanations

    charitable programs and foundations

    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_22/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
     you
    -1.28
     Polskiej
    -1.02
     dotyczące
    -1.00
    X
    -1.00
    時間で
    -0.99
    ,
    -0.98
     wohnen
    -0.98
     or
    -0.96
     
    -0.96
     рады
    -0.95
    POSITIVE LOGITS
     program
    1.43
     프로그램
    1.23
    Stiftung
    1.16
     volunteer
    1.12
     programs
    1.10
     krás
    1.07
    çim
    1.06
     програ
    1.06
     scheme
    1.05
     project
    1.04
    Activations Density 0.056%

    No Known Activations