© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129011
    Prev
    Next
    INDEX
    Explanations

    optimistic outlook

    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
     such
    -1.70
    Elaboración
    -1.59
     Públicas
    -1.59
     Hacer
    -1.58
     Cuando
    -1.58
    Algunos
    -1.49
    Cuando
    -1.48
     Köz
    -1.48
    I
    -1.48
    皝
    -1.47
    POSITIVE LOGITS
     chances
    1.74
     tiden
    1.60
    \
    1.59
    {
    1.54
     hjälp
    1.50
    種類の
    1.50
     prospects
    1.49
     块
    1.48
    手中的
    1.46
     anledning
    1.42
    Activations Density 0.014%

    No Known Activations