© 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. 85662
    Prev
    Next
    INDEX
    Explanations

    various languages

    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
     säga
    -1.74
     एवं
    -1.71
    博多
    -1.68
     sagde
    -1.66
    紧紧
    -1.63
    拚
    -1.58
    owners
    -1.57
    🕗
    -1.56
     sekä
    -1.55
    瑧
    -1.55
    POSITIVE LOGITS
     then
    2.27
    ᯾
    2.08
     '
    2.02
     of
    1.82
     akkor
    1.74
    比如说
    1.69
    '
    1.66
    anleitung
    1.66
    áculo
    1.64
    tênis
    1.59
    Activations Density 0.031%

    No Known Activations