© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 68015
    Prev
    Next
    INDEX
    Explanations

    operating systems, apps, money, countries

    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
    bezpiecz
    -1.21
    ७
    -1.09
     anledning
    -1.09
     chrétienne
    -1.07
     нам
    -1.04
     myś
    -1.03
    šanās
    -1.03
    ALSO
    -1.03
    }],
    
    -1.03
     Classical
    -1.02
    POSITIVE LOGITS
     desmotiv
    1.20
     একটি
    1.20
     etc
    1.19
    Etapa
    1.17
     nimmer
    1.16
     or
    1.13
    ೬
    1.10
     určit
    1.08
     casar
    1.08
     xadrez
    1.06
    Activations Density 0.031%

    No Known Activations