© 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. 59243
    Prev
    Next
    INDEX
    Explanations

    degrees celsius

    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
    Can
    -0.91
     really
    -0.90
     inapropiados
    -0.88
     what
    -0.87
     from
    -0.80
     new
    -0.79
    Vorlage
    -0.79
     can
    -0.78
     such
    -0.78
     For
    -0.78
    POSITIVE LOGITS
     scorching
    0.98
     vych
    0.91
    Nand
    0.90
     mantém
    0.89
     dismal
    0.86
     temperatures
    0.85
     mał
    0.84
    Matériel
    0.84
     rhino
    0.84
     différentes
    0.84
    Activations Density 0.003%

    No Known Activations