© 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. 59909
    Prev
    Next
    INDEX
    Explanations

    section headers

    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
     Também
    -1.70
     also
    -1.69
     também
    -1.61
     également
    -1.55
     ataca
    -1.52
     terrenos
    -1.46
     blok
    -1.45
     rapporter
    -1.45
     xícara
    -1.45
     helicópter
    -1.45
    POSITIVE LOGITS
    :
    2.11
    a
    2.00
    *
    1.98
     in
    1.73
     by
    1.65
    da
    1.63
    am
    1.54
     Any
    1.53
    Any
    1.53
     و
    1.53
    Activations Density 0.101%

    No Known Activations