© 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. 66623
    Prev
    Next
    INDEX
    Explanations

    foreign language content

    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
    SIZES
    -1.04
    Exeunt
    -0.98
    LEBR
    -0.91
    はその
    -0.91
     narkoba
    -0.91
    OrNil
    -0.89
     rör
    -0.89
     спектак
    -0.88
     kakak
    -0.88
    днев
    -0.88
    POSITIVE LOGITS
    oggi
    1.03
    為に
    0.98
    ところです
    0.96
    範圍
    0.94
    المنا
    0.94
     Zuhause
    0.94
     菜单
    0.94
    furl
    0.93
     ruedas
    0.93
     empuj
    0.92
    Activations Density 0.000%

    No Known Activations