© 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. 34-GEMMASCOPE-RES-131K
    7. 2287
    Prev
    Next
    INDEX
    Explanations

    km from

    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_34/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
    ֿ
    -0.91
    <table>
    -0.90
     ית
    -0.87
    ícia
    -0.85
    __("
    -0.80
    lización
    -0.79
    PRISE
    -0.77
    chunks
    -0.77
    డ్
    -0.76
    ıyor
    -0.75
    POSITIVE LOGITS
     amplio
    0.87
     долларов
    0.85
     verurs
    0.77
     verseny
    0.77
     reissue
    0.77
    nl
    0.75
     литров
    0.74
     erneu
    0.73
    衫
    0.72
     Hebrews
    0.71
    Activations Density 0.008%

    No Known Activations