© 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. 100541
    Prev
    Next
    INDEX
    Explanations

    sharing thoughts and opinions

    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
    籏
    -1.75
     dengan
    -1.75
    傒
    -1.73
    chige
    -1.68
    晙
    -1.65
    
    -1.59
    Zubereitung
    -1.57
    崀
    -1.57
     was
    -1.55
    থ্য
    -1.53
    POSITIVE LOGITS
     about
    2.06
    .
    1.66
     on
    1.64
     dispozici
    1.50
    L
    1.48
    و
    1.45
    .''
    1.41
    อีก
    1.34
     again
    1.32
     '
    1.30
    Activations Density 0.040%

    No Known Activations