© 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. 10-GEMMASCOPE-RES-131K
    7. 57440
    Prev
    Next
    INDEX
    Explanations

    to actions

    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
     for
    -2.05
     शुर
    -1.80
     providing
    -1.76
     bepaald
    -1.58
     that
    -1.56
    嗵
    -1.56
    嗞
    -1.53
    の葉
    -1.52
     superbly
    -1.50
    ためには
    -1.49
    POSITIVE LOGITS
     dreary
    1.98
    enablog
    1.91
    vignon
    1.90
    ጐ
    1.88
    9
    1.86
     работают
    1.77
    esthes
    1.71
     informaron
    1.70
     Dinas
    1.68
    4
    1.66
    Activations Density 0.006%

    No Known Activations