© 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. 130850
    Prev
    Next
    INDEX
    Explanations

    start process or related context

    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
     umano
    -1.30
     and
    -1.18
     asiático
    -1.13
     africano
    -1.12
     Oggi
    -1.10
     tecnologie
    -1.07
     Američ
    -1.02
    ℭ
    -1.02
    moreland
    -1.01
    ෑ
    -1.01
    POSITIVE LOGITS
    ۔
    1.02
     some
    1.00
    𝐠
    0.95
     nonetheless
    0.94
    开
    0.93
    Fernseh
    0.93
    ể
    0.90
     menjelaskan
    0.88
     miesięcy
    0.88
     häls
    0.87
    Activations Density 0.036%

    No Known Activations