© 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. 39639
    Prev
    Next
    INDEX
    Explanations

    all are confirmed

    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
    -1.81
    蓠
    -1.77
     \
    -1.73
     toutes
    -1.72
    戋
    -1.56
    unfortunately
    -1.49
     سایر
    -1.47
     realmente
    -1.47
    
    -1.47
     enorm
    -1.46
    POSITIVE LOGITS
    蕯
    1.96
     innumerable
    1.79
     området
    1.71
     medlemmer
    1.66
     makes
    1.66
    Transcripción
    1.59
     dozens
    1.57
     aktivitet
    1.57
    性質
    1.56
    Transcriptie
    1.56
    Activations Density 0.066%

    No Known Activations