© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 75636
    Prev
    Next
    INDEX
    Explanations

    key-value pairs

    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_10/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
    BeginInit
    -1.16
     siglas
    -1.13
     FontWeight
    -1.09
    ضور
    -1.05
    //};
    -1.00
     of
    -0.97
     noch
    -0.96
     oleh
    -0.96
     durch
    -0.95
     jardín
    -0.94
    POSITIVE LOGITS
    lieu
    1.16
    selho
    1.08
    them
    1.07
    description
    1.07
    before
    1.05
    これ
    1.04
     считают
    1.03
    currentPosition
    1.03
     thereof
    1.00
     descriptions
    0.97
    Activations Density 0.222%

    No Known Activations