© 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. 104293
    Prev
    Next
    INDEX
    Explanations

    news and reports from Europe

    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
     to
    -1.29
     from
    -1.07
    子さん
    -1.04
     in
    -1.00
    ⋯
    -0.96
    ležité
    -0.95
    razione
    -0.95
     if
    -0.94
    ClientSize
    -0.94
     my
    -0.92
    POSITIVE LOGITS
     adelantado
    1.16
    悽
    1.15
    ⾼
    1.12
     entregó
    1.11
     ajustado
    1.06
     keuze
    1.02
     news
    1.00
    EUROPE
    0.99
     yesterday
    0.99
     rapporter
    0.98
    Activations Density 0.006%

    No Known Activations