© 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. 20159
    Prev
    Next
    INDEX
    Explanations

    eslint disable ignore comments

    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
     römischen
    -1.52
     valioso
    -1.50
     reservado
    -1.47
    やってきた
    -1.45
    uero
    -1.43
     decorado
    -1.41
    変わる
    -1.40
     amarela
    -1.39
     colorida
    -1.39
     öffentlichen
    -1.39
    POSITIVE LOGITS
     of
    1.84
    y
    1.74
    洐
    1.67
    。
    1.55
    ine
    1.51
    怍
    1.49
    %``
    1.46
     begitu
    1.40
    itées
    1.40
     hujan
    1.39
    Activations Density 0.005%

    No Known Activations