© 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. 25589
    Prev
    Next
    INDEX
    Explanations

    copyright or license headers

    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
    ּוֹ
    -1.21
     flexible
    -1.09
     financial
    -1.02
     for
    -1.00
     joten
    -0.93
     scope
    -0.93
    ִּ
    -0.92
     flexib
    -0.91
     grant
    -0.91
     Neben
    -0.90
    POSITIVE LOGITS
     catholique
    1.09
    maintain
    1.09
     serai
    1.05
     pâte
    0.96
     salade
    0.96
     chrétienne
    0.96
     poire
    0.93
    initely
    0.93
    papar
    0.90
     lucu
    0.88
    Activations Density 0.003%

    No Known Activations