© 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. 34-GEMMASCOPE-RES-131K
    7. 99846
    Prev
    Next
    INDEX
    Explanations

    technical questions and code

    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_34/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
    Ой
    -0.85
     hébergement
    -0.81
     DEPOSITORY
    -0.79
    оборот
    -0.73
     colère
    -0.71
     насеља
    -0.71
    espé
    -0.71
    Mutagenicity
    -0.71
     člove
    -0.71
     används
    -0.71
    POSITIVE LOGITS
     Georgetown
    1.01
    達成
    0.93
    GHI
    0.85
    mvc
    0.85
    IOM
    0.83
     hii
    0.82
    klub
    0.82
    TIN
    0.81
    layoutParams
    0.80
    chay
    0.80
    Activations Density 0.013%

    No Known Activations