© 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. 58456
    Prev
    Next
    INDEX
    Explanations

    humidity controlled

    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
     at
    -1.08
     all
    -0.96
     people
    -0.92
     make
    -0.91
     one
    -0.90
     or
    -0.88
     so
    -0.87
     sophisticated
    -0.86
     get
    -0.86
     has
    -0.85
    POSITIVE LOGITS
    Ihre
    1.01
    foods
    1.00
    
    0.97
    why
    0.96
     MILES
    0.95
     maniere
    0.94
    
    0.94
    ܆
    0.93
     plancher
    0.93
    Schriften
    0.92
    Activations Density 0.005%

    No Known Activations