© 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. 111630
    Prev
    Next
    INDEX
    Explanations

    holding that

    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
    螣
    -1.83
     затем
    -1.73
    Unmarshaller
    -1.71
     («
    -1.70
     \"
    -1.66
     puis
    -1.55
    感じ
    -1.55
     (...)
    -1.53
    prepareStatement
    -1.50
     в
    -1.49
    POSITIVE LOGITS
    9
    1.96
    2
    1.82
    1
    1.79
    4
    1.76
     varandra
    1.73
     dificuldades
    1.73
    杁
    1.73
     grij
    1.70
     sicheren
    1.69
     that
    1.67
    Activations Density 0.006%

    No Known Activations