© 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. 26437
    Prev
    Next
    INDEX
    Explanations

    demonstratives followed by names

    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
     people
    -1.16
     someone
    -1.04
     Vasquez
    -1.03
     that
    -1.03
     做法
    -1.03
    ブリッド
    -1.02
     aplikacji
    -1.02
     gần
    -1.02
    layoutControl
    -1.01
     convinced
    -1.00
    POSITIVE LOGITS
     this
    1.75
     these
    1.54
     هذه
    1.48
     dieser
    1.38
    these
    1.30
     cette
    1.27
     این
    1.27
    this
    1.27
    はこの
    1.22
     ఈ
    1.19
    Activations Density 0.037%

    No Known Activations