© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44363
    Prev
    Next
    INDEX
    Explanations

    prosecutorial or Qin

    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
     This
    -4.31
     uber
    -3.22
     That
    -2.98
    d
    -2.92
     Diese
    -2.88
     Those
    -2.86
     dieses
    -2.80
     With
    -2.73
    ,''
    -2.73
    ࿚
    -2.72
    POSITIVE LOGITS
    艽
    3.36
    岨
    3.09
    蟶
    2.97
    such
    2.94
     renowned
    2.77
    幛
    2.70
     erhi
    2.69
    萇
    2.59
    
    2.56
    镚
    2.53
    Activations Density 0.001%

    No Known Activations