© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106668
    Prev
    Next
    INDEX
    Explanations

    architectural styles and terms

    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
    ffions
    -0.85
     Kamar
    -0.83
     sağlar
    -0.82
    kate
    -0.81
    EPO
    -0.77
    illères
    -0.76
    ูล
    -0.75
    mathsf
    -0.74
     meminta
    -0.73
    mcc
    -0.73
    POSITIVE LOGITS
     Ionic
    1.45
     columns
    1.36
     Dor
    1.30
     ionic
    1.29
     Corinth
    1.28
    column
    1.21
    Ionic
    1.20
     column
    1.17
    columns
    1.14
     Columns
    1.14
    Activations Density 0.016%

    No Known Activations