© 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. 22-GEMMASCOPE-RES-131K
    7. 129955
    Prev
    Next
    INDEX
    Explanations

    file paths and headers

    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
     après
    -1.11
    และ
    -1.07
    mobileqq
    -1.05
     seperti
    -1.02
    ikuti
    -1.02
    зум
    -1.01
    idenz
    -1.00
    mudah
    -1.00
     desfile
    -0.99
    UIControlState
    -0.98
    POSITIVE LOGITS
     quegli
    0.93
    interact
    0.93
    ving
    0.92
    inet
    0.92
     входят
    0.90
    inn
    0.90
     появляется
    0.88
     становятся
    0.87
    ynn
    0.85
     habiendo
    0.85
    Activations Density 0.009%

    No Known Activations