© 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. 66318
    Prev
    Next
    INDEX
    Explanations

    degree of change or comparison

    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
     السياس
    -1.49
     gancho
    -1.15
     cansado
    -1.13
     görd
    -1.10
     heridos
    -1.10
    Waga
    -1.09
    Interes
    -1.08
    regelen
    -1.06
    方針
    -1.06
    Dimens
    -1.05
    POSITIVE LOGITS
    Šaltiniai
    1.30
     overall
    1.23
     电影
    1.18
     performance
    1.14
     increase
    1.05
    ^{\
    1.05
     increased
    1.02
     not
    1.02
     huo
    1.01
     游戏
    1.00
    Activations Density 0.034%

    No Known Activations