© 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. 10-GEMMASCOPE-RES-131K
    7. 59246
    Prev
    Next
    INDEX
    Explanations

    electronic circuits

    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
    囮
    -1.76
    鳏
    -1.70
    {
    -1.61
    的表现
    -1.55
    灕
    -1.50
    栝
    -1.50
    垆
    -1.49
    下一篇
    -1.48
    ܃
    -1.47
    嗳
    -1.46
    POSITIVE LOGITS
    1.99
     gleichen
    1.96
     Gegensatz
    1.95
     cuando
    1.94
    两个
    1.90
     selben
    1.89
     Ersten
    1.88
    }
    1.79
     ){
    1.76
    <bos>
    1.74
    Activations Density 0.028%

    No Known Activations