© 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. 14721
    Prev
    Next
    INDEX
    Explanations

    greatest followed by nouns

    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
    
    -1.80
    虓
    -1.73
    炱
    -1.67
    珰
    -1.63
    pherds
    -1.63
    齜
    -1.62
    뮐
    -1.62
    示意图
    -1.61
    釤
    -1.60
    埛
    -1.60
    POSITIVE LOGITS
    ↵
    2.34
     of
    2.13
     Shortly
    1.56
     With
    1.54
     no
    1.54
    </h2>
    1.54
    During
    1.52
    5
    1.52
    E
    1.51
     great
    1.50
    Activations Density 0.032%

    No Known Activations