© 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. 62819
    Prev
    Next
    INDEX
    Explanations

    shipping methods

    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
    otry
    -0.77
     administrar
    -0.76
    त्व
    -0.76
     まとめ
    -0.75
     próprias
    -0.74
    ısından
    -0.74
    ञ
    -0.74
     ideias
    -0.74
    vård
    -0.73
    sement
    -0.73
    POSITIVE LOGITS
     overnight
    1.97
     Overnight
    1.90
     expedited
    1.80
    Overnight
    1.63
     express
    1.63
     Express
    1.63
    Express
    1.60
    express
    1.44
     rush
    1.38
     Priority
    1.37
    Activations Density 0.041%

    No Known Activations