© 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. 72488
    Prev
    Next
    INDEX
    Explanations

    abstract concepts or qualities

    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
    游戏的
    -0.96
     blijkt
    -0.89
    ándolos
    -0.86
     construite
    -0.84
    ができます
    -0.83
     Città
    -0.82
     pół
    -0.82
    ısını
    -0.81
    的一种
    -0.80
    niosek
    -0.79
    POSITIVE LOGITS
    ivably
    0.96
     می‌گو
    0.93
    `,`
    0.91
    》，
    0.90
    Джерела
    0.90
    nemonic
    0.87
     how
    0.87
    "=>"
    0.85
    udo
    0.84
    CTG
    0.83
    Activations Density 0.066%

    No Known Activations