© 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. 13610
    Prev
    Next
    INDEX
    Explanations

    QB or Este Taller

    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
    *
    -1.47
    "
    -1.43
    宮城
    -1.38
    :
    -1.36
     some
    -1.27
    〰
    -1.27
     всех
    -1.25
    说
    -1.24
    nagyobb
    -1.23
    饺子
    -1.23
    POSITIVE LOGITS
    佯
    1.56
     are
    1.52
     vuestra
    1.48
    ibouti
    1.46
     ejecuta
    1.43
     logística
    1.41
    kitan
    1.40
     erstes
    1.40
     auß
    1.37
    IGHT
    1.36
    Activations Density 0.044%

    No Known Activations