© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43034
    Prev
    Next
    INDEX
    Explanations

    positive evaluation of quality

    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
    ارتمان
    -1.68
     parfü
    -1.59
    辄
    -1.57
    Ordinary
    -1.52
    yarakat
    -1.49
    嫑
    -1.48
    蚰
    -1.48
     defekt
    -1.47
    後記
    -1.46
    變成
    -1.43
    POSITIVE LOGITS
    ");
    1.64
    e
    1.51
    as
    1.40
     hasilnya
    1.40
     namun
    1.38
     welches
    1.36
     corações
    1.34
     see
    1.34
     segun
    1.34
     長袖
    1.31
    Activations Density 0.006%

    No Known Activations