© 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. 10-GEMMASCOPE-RES-131K
    7. 65446
    Prev
    Next
    INDEX
    Explanations

    golang os and log packages

    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_10/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
    </b>
    -2.55
     fühlen
    -1.59
     verschillende
    -1.54
     detaylı
    -1.53
    }{
    -1.53
     MUCH
    -1.52
    </sup>
    -1.50
     ürünleri
    -1.48
    );
    -1.48
    phère
    -1.47
    POSITIVE LOGITS
     you
    2.08
    </h3>
    2.06
    because
    1.70
    珖
    1.60
    偸
    1.56
    ムラ
    1.47
    芣
    1.46
    نك
    1.46
    สำหรับ
    1.45
     encargado
    1.41
    Activations Density 0.012%

    No Known Activations