© 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. 15139
    Prev
    Next
    INDEX
    Explanations

    code blocks and structured data

    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
    Varian
    -1.04
    CARACTERÍSTICAS
    -0.96
    CONTENIDO
    -0.96
    INDICE
    -0.91
    élite
    -0.91
    DESCRIPCIÓN
    -0.91
     wollten
    -0.90
    SALUD
    -0.90
    外部链接
    -0.89
     Aufführung
    -0.88
    POSITIVE LOGITS
     untersucht
    0.96
    bitol
    0.93
    ·
    0.89
              
    0.85
    BURGH
    0.85
                  
    0.84
    oughlin
    0.80
    没有什么
    0.80
    VE
    0.79
    span
    0.78
    Activations Density 0.003%

    No Known Activations