© 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. 31001
    Prev
    Next
    INDEX
    Explanations

    published stories

    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
     cable
    -1.13
     cables
    -1.01
    Cable
    -1.00
     Cable
    -0.96
    cable
    -0.89
     CABLE
    -0.87
    nyv
    -0.85
     Cables
    -0.83
     кабе
    -0.81
     Mio
    -0.79
    POSITIVE LOGITS
     pulp
    1.23
     stories
    0.94
     revistas
    0.94
     histórias
    0.91
     STORIES
    0.90
     Stories
    0.88
    ضير
    0.84
    Stories
    0.83
     story
    0.81
     condensation
    0.79
    Activations Density 0.055%

    No Known Activations