© 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. 34-GEMMASCOPE-RES-131K
    7. 102995
    Prev
    Next
    INDEX
    Explanations

    jūrų, Jäg, jízd, Jork, Järn, Jägala, Jaén, Jarem, Jutland, Iaşi

    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_34/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
     middel
    -0.82
     Wirtschafts
    -0.81
    ciem
    -0.75
     doit
    -0.74
     adat
    -0.73
    стреча
    -0.71
    digung
    -0.70
     fullt
    -0.70
     Brent
    -0.70
     ス
    -0.69
    POSITIVE LOGITS
     richiesto
    0.88
     meski
    0.87
     meskipun
    0.85
     attiva
    0.82
    oltre
    0.81
     starken
    0.81
     personalmente
    0.80
    ppar
    0.80
     besonderes
    0.79
     berühmten
    0.79
    Activations Density 0.016%

    No Known Activations