© 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. 22-GEMMASCOPE-RES-131K
    7. 72025
    Prev
    Next
    INDEX
    Explanations

    newly created record id

    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_22/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
     achats
    -0.97
    Źródło
    -0.96
     مفص
    -0.89
     vélos
    -0.87
     boî
    -0.87
    activités
    -0.86
    來
    -0.86
    ⁕
    -0.85
     ᾿
    -0.85
    gmt
    -0.85
    POSITIVE LOGITS
     new
    1.37
     newly
    1.20
     after
    1.08
     created
    1.05
     success
    1.01
     successes
    0.95
     notable
    0.94
     creation
    0.93
    亮点
    0.92
     durable
    0.91
    Activations Density 0.026%

    No Known Activations