© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20807
    Prev
    Next
    INDEX
    Explanations

    HTML and programming code structure

    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_10/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
     áudio
    -1.35
     auster
    -1.29
     linhas
    -1.24
     correto
    -1.23
     suav
    -1.23
    donde
    -1.23
     kellett
    -1.23
    迸
    -1.23
     confron
    -1.23
    actually
    -1.23
    POSITIVE LOGITS
     use
    1.84
     uses
    1.56
     first
    1.48
     produces
    1.45
     one
    1.39
     increase
    1.37
     because
    1.33
    áním
    1.29
     and
    1.29
     with
    1.28
    Activations Density 0.312%

    No Known Activations