© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68484
    Prev
    Next
    INDEX
    Explanations

    entrance and hallways

    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
    Negative Logits
    5
    -1.75
    S
    -1.73
    di
    -1.67
    6
    -1.62
    mon
    -1.61
    ta
    -1.57
    ti
    -1.55
    <i>
    -1.51
    M
    -1.50
     forskellige
    -1.49
    POSITIVE LOGITS
     Compared
    1.43
     programmation
    1.42
    ANTES
    1.39
    вні
    1.37
     總
    1.36
     Originally
    1.35
     There
    1.34
    錚
    1.34
    جمة
    1.34
     dagli
    1.33
    Activations Density 0.006%

    No Known Activations