© 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. 10-GEMMASCOPE-RES-131K
    7. 14986
    Prev
    Next
    INDEX
    Explanations

    Panama, Panama City, or Clinic/Anne

    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_10/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
    7
    -3.56
    8
    -3.36
    9
    -3.33
    4
    -3.08
    鶿
    -2.84
     genaue
    -2.83
     vollständige
    -2.83
    3
    -2.81
     wahre
    -2.69
    6
    -2.58
    POSITIVE LOGITS
     Interestingly
    2.63
     Ironically
    2.58
     Surprisingly
    2.50
    ↵
    2.39
     Both
    2.34
     Originally
    2.33
     Considering
    2.33
     Combining
    2.30
     یک
    2.27
     Usually
    2.27
    Activations Density 0.004%

    No Known Activations