© 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. 34-GEMMASCOPE-RES-131K
    7. 30038
    Prev
    Next
    INDEX
    Explanations

    volumes or sections

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     typename
    -0.77
    thaler
    -0.75
    MenuInflater
    -0.75
    Další
    -0.74
    爐
    -0.73
    ੍ਹ
    -0.72
    洸
    -0.72
    Marx
    -0.72
    ubel
    -0.71
    FirebaseUser
    -0.71
    POSITIVE LOGITS
    یشه
    0.90
    堑
    0.80
    neder
    0.78
    Mord
    0.76
     scraping
    0.75
     Rabin
    0.74
     Ape
    0.73
    MARTIN
    0.73
    qj
    0.73
    šč
    0.72
    Activations Density 0.041%

    No Known Activations