© 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. 22-GEMMASCOPE-RES-131K
    7. 66179
    Prev
    Next
    INDEX
    Explanations

    Free speech, eye roll, investigation on

    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
    gitte
    -1.11
     бампер
    -1.05
     Erbe
    -1.02
     find
    -0.96
     in
    -0.95
     using
    -0.94
    вен
    -0.94
     OBITUARY
    -0.92
    кнул
    -0.91
     out
    -0.91
    POSITIVE LOGITS
    bilden
    1.45
     cukru
    1.41
     klubu
    1.27
     óculos
    1.23
     acessórios
    1.20
     énorme
    1.18
    kontakt
    1.16
    yled
    1.16
     levier
    1.14
    鹩
    1.14
    Activations Density 0.002%

    No Known Activations