© 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. 45180
    Prev
    Next
    INDEX
    Explanations

    how to, want to, does anyone

    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
     of
    -1.68
     ず
    -1.64
     jūs
    -1.55
     viena
    -1.54
     auguri
    -1.50
     plupart
    -1.48
    Svara
    -1.46
    鈰
    -1.46
    學院
    -1.46
    .’
    -1.45
    POSITIVE LOGITS
     '
    2.16
     was
    1.85
     contó
    1.55
    に行く
    1.47
     usado
    1.44
     '-
    1.42
     influenci
    1.41
     músculo
    1.41
    住了
    1.36
    に行って
    1.35
    Activations Density 0.029%

    No Known Activations