© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32175
    Prev
    Next
    INDEX
    Explanations

    gloves, trait, Share, Two, my, Be

    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
    Not in Any Lists

    No Comments

    Negative Logits
     TAG
    -0.80
    んだろう
    -0.77
    Local
    -0.76
    base
    -0.75
    zeum
    -0.73
    承受
    -0.73
     cavallo
    -0.73
     RFI
    -0.73
     Đây
    -0.73
     MAGIC
    -0.72
    POSITIVE LOGITS
     gloves
    0.96
    学生
    0.88
     Gloves
    0.80
     philosophers
    0.77
     growers
    0.77
     set
    0.76
    会館
    0.76
     Pieces
    0.75
     obten
    0.73
     belt
    0.73
    Activations Density 0.011%

    No Known Activations