© 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. 102447
    Prev
    Next
    INDEX
    Explanations

    carried out

    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
    鱟
    -2.27
     a
    -1.88
    ⃙
    -1.75
    </b>
    -1.74
    鼙
    -1.72
     линия
    -1.66
     evidente
    -1.66
    B
    -1.63
    例えば
    -1.60
    ที่จะ
    -1.59
    POSITIVE LOGITS
    乆
    2.17
     These
    2.16
     frattempo
    1.94
     técn
    1.90
    Another
    1.90
    歺
    1.80
    
    1.78
     Antwerpen
    1.77
     veicolo
    1.77
     anún
    1.75
    Activations Density 0.013%

    No Known Activations