© 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. 22-GEMMASCOPE-RES-131K
    7. 130566
    Prev
    Next
    INDEX
    Explanations

    links and code snippets

    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
    Pemer
    -0.94
     Informações
    -0.91
     privados
    -0.90
    꽃
    -0.86
     geli
    -0.82
    tualmente
    -0.81
    белый
    -0.81
    Karakter
    -0.80
    ዲ
    -0.79
    brück
    -0.78
    POSITIVE LOGITS
     *
    0.81
     }^{*}
    0.80
    ctober
    0.79
     MOMENT
    0.79
    脾
    0.78
     pequeño
    0.76
    他也
    0.76
    ICC
    0.75
     émotion
    0.75
     što
    0.75
    Activations Density 0.059%

    No Known Activations