© 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. 117985
    Prev
    Next
    INDEX
    Explanations

    in the form of

    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
     emisiones
    -0.97
     exportaciones
    -0.91
     précédemment
    -0.89
     tijdens
    -0.88
     humedad
    -0.87
     energías
    -0.85
     progressivement
    -0.85
     zaradi
    -0.85
     isolé
    -0.84
     Conj
    -0.81
    POSITIVE LOGITS
     in
    3.92
     berupa
    3.69
     berbentuk
    2.36
     בצ
    1.81
     виде
    1.56
     dạng
    1.52
     form
    1.44
     postaci
    1.44
     shaped
    1.30
     σε
    1.30
    Activations Density 0.215%

    No Known Activations