© 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. 34-GEMMASCOPE-RES-131K
    7. 91160
    Prev
    Next
    INDEX
    Explanations

    version numbers and specific question formats

    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
     comments
    -0.84
    𝐆
    -0.75
    comment
    -0.75
     heard
    -0.73
     avez
    -0.73
     comment
    -0.73
     import
    -0.73
    FINAL
    -0.72
    final
    -0.71
     difficulties
    -0.71
    POSITIVE LOGITS
     chore
    1.03
    ilich
    0.87
    ثة
    0.85
     between
    0.82
    orche
    0.81
     Chore
    0.80
    บัติ
    0.79
    Chore
    0.78
    新たに
    0.77
     thanks
    0.77
    Activations Density 0.041%

    No Known Activations