© 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. 9251
    Prev
    Next
    INDEX
    Explanations

    directory path and build configuration

    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
    5
    -3.58
    0
    -3.31
    6
    -3.11
    9
    -3.11
    8
    -2.94
    When
    -2.77
     or
    -2.75
    Despite
    -2.70
     When
    -2.70
    7
    -2.66
    POSITIVE LOGITS
     quintessential
    2.78
    趿
    2.75
     vijf
    2.70
    犼
    2.59
     whom
    2.56
     และ
    2.52
     predominantly
    2.48
    
    2.48
     sieben
    2.47
    說
    2.44
    Activations Density 0.069%

    No Known Activations