© 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. 34120
    Prev
    Next
    INDEX
    Explanations

    creationist vs. evolutionary arguments

    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
     will
    -1.22
    JMenuBar
    -1.19
    thenia
    -1.11
    ılır
    -1.04
     onCreateView
    -1.03
    。
    -1.02
    </tfoot>
    -1.02
    AppRoutingModule
    -0.99
    CloseOperation
    -0.99
    SuspendLayout
    -0.98
    POSITIVE LOGITS
     asisten
    1.39
     zudem
    1.38
     religieux
    1.30
     chré
    1.28
    ଦ
    1.24
    Additionally
    1.23
     dejen
    1.20
    DETAILED
    1.20
     linho
    1.18
    সূত্র
    1.17
    Activations Density 0.024%

    No Known Activations