© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 82986
    Prev
    Next
    INDEX
    Explanations

    starts with Il or Ill

    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
    🍧
    -0.90
     Stanisław
    -0.84
    🍫
    -0.82
    epiece
    -0.82
    随
    -0.81
    Planning
    -0.80
     moule
    -0.80
    ін
    -0.79
    ℍ
    -0.78
     Sebastián
    -0.78
    POSITIVE LOGITS
     ehemalige
    0.77
    Bedrooms
    0.77
     bestimmte
    0.75
     названием
    0.73
    怎
    0.69
     IL
    0.68
    xymatrix
    0.68
     maybe
    0.68
     energies
    0.67
     things
    0.67
    Activations Density 0.030%

    No Known Activations