© 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. 57401
    Prev
    Next
    INDEX
    Explanations

    HTML attributes and code snippets

    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
    in
    -1.80
    on
    -1.64
     we
    -1.45
     after
    -1.41
    k
    -1.40
    w
    -1.39
    N
    -1.38
     زیرا
    -1.38
    no
    -1.37
    OP
    -1.37
    POSITIVE LOGITS
    יצד
    1.50
    realme
    1.41
    goodbye
    1.41
    Ꮀ
    1.37
    shimano
    1.37
    Eventos
    1.37
    redmi
    1.35
     mencionó
    1.34
     añadió
    1.33
    teatro
    1.33
    Activations Density 0.393%

    No Known Activations