© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 104507
    Prev
    Next
    INDEX
    Explanations

    California universities

    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
    錾
    -1.30
     inclus
    -1.29
    繙
    -1.22
     và
    -1.16
     claves
    -1.16
     และ
    -1.16
    henswürdigkeiten
    -1.14
     criatura
    -1.13
    -------------</
    -1.12
    restling
    -1.10
    POSITIVE LOGITS
    bánh
    1.19
     there
    1.17
     rých
    1.15
     ľah
    1.13
    köz
    1.01
     what
    1.00
     дія
    0.98
     not
    0.98
    wały
    0.98
     pomocou
    0.98
    Activations Density 0.027%

    No Known Activations