© 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. 137
    Prev
    Next
    INDEX
    Explanations

    Benny or Dani followed by a name

    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
     ที่
    -2.56
     descuentos
    -2.34
     longterm
    -2.33
     fruitless
    -2.31
     acepta
    -2.25
     desafi
    -2.23
     regrettable
    -2.23
     futile
    -2.22
     carrinho
    -2.20
     италья
    -2.20
    POSITIVE LOGITS
    {
    3.03
     carbone
    2.66
    With
    2.56
    独特
    2.45
    0
    2.42
    تیجه
    2.41
    …”
    2.28
    In
    2.27
    　（
    2.25
    丏
    2.25
    Activations Density 0.004%

    No Known Activations