© 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. 49151
    Prev
    Next
    INDEX
    Explanations

    code comments and separators

    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
     encryption
    -0.84
     informatique
    -0.79
    ctron
    -0.75
    liferation
    -0.75
    に移
    -0.73
    寄
    -0.71
     friction
    -0.71
     ocasiones
    -0.70
    лакти
    -0.69
     excavation
    -0.68
    POSITIVE LOGITS
    远程
    0.79
     Dank
    0.78
    Dank
    0.74
     ステ
    0.72
     パーク
    0.71
    peq
    0.69
    Across
    0.68
     CBE
    0.67
    oodoo
    0.67
    callback
    0.67
    Activations Density 0.024%

    No Known Activations