© 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. 105307
    Prev
    Next
    INDEX
    Explanations

    has to offer

    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
    aculture
    -1.69
     kompati
    -1.65
    车上
    -1.52
    rha
    -1.51
     amables
    -1.49
    やろ
    -1.49
    )$\\
    -1.49
    oves
    -1.47
    underland
    -1.46
     galería
    -1.46
    POSITIVE LOGITS
     Firstly
    1.80
     Neither
    1.76
     of
    1.73
     Anliegen
    1.69
    le
    1.59
     Instead
    1.54
     Namely
    1.54
     Until
    1.52
     ambivalent
    1.49
     Throughout
    1.48
    Activations Density 0.008%

    No Known Activations