© 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. 34-GEMMASCOPE-RES-131K
    7. 78632
    Prev
    Next
    INDEX
    Explanations

    BLM Gold winning WHO Roy

    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
     shopping
    -0.90
    shopping
    -0.86
     Horowitz
    -0.85
    engue
    -0.82
     msk
    -0.81
     スタジオ
    -0.78
    gás
    -0.76
     Frankfort
    -0.75
     SHOPPING
    -0.75
     ltd
    -0.74
    POSITIVE LOGITS
     BLM
    1.45
    BLM
    1.19
     Bureau
    0.90
    Surface
    0.89
    Bureau
    0.85
     Surface
    0.81
     Decision
    0.79
     surface
    0.79
     BUREAU
    0.79
    analysis
    0.79
    Activations Density 0.023%

    No Known Activations