© 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. 22-GEMMASCOPE-RES-131K
    7. 73446
    Prev
    Next
    INDEX
    Explanations

    .html and variables

    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_22/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
     with
    -0.96
     when
    -0.93
     as
    -0.88
     while
    -0.84
     This
    -0.84
    umpulan
    -0.81
     during
    -0.81
     ensure
    -0.80
    Nicholas
    -0.79
     protect
    -0.78
    POSITIVE LOGITS
     cabelo
    0.97
     algodão
    0.93
     couro
    0.92
     equipamento
    0.91
    梦幻
    0.89
     usuário
    0.87
     féd
    0.87
    倅
    0.87
     disant
    0.86
     lieve
    0.85
    Activations Density 0.168%

    No Known Activations