© 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. 64830
    Prev
    Next
    INDEX
    Explanations

    parts of identifiers

    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
     rides
    -0.86
     diary
    -0.84
     describe
    -0.79
    rdag
    -0.79
     sha
    -0.79
    かけた
    -0.73
     прото
    -0.73
     overheard
    -0.73
     diaper
    -0.73
     vest
    -0.73
    POSITIVE LOGITS
     Gideon
    0.93
     piscine
    0.93
     Bibles
    0.84
     offensi
    0.84
    工具
    0.82
     PUBLISHING
    0.82
     Testa
    0.79
    reading
    0.79
    番茄
    0.79
     Translation
    0.79
    Activations Density 0.024%

    No Known Activations