© 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. 109277
    Prev
    Next
    INDEX
    Explanations

    steps and directions

    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
    nende
    -0.92
    лку
    -0.75
    raisals
    -0.74
    🧵
    -0.71
    örter
    -0.71
    Quotes
    -0.70
    fect
    -0.70
    ➝
    -0.69
     kuni
    -0.69
    診断
    -0.68
    POSITIVE LOGITS
     instructions
    7.41
    instructions
    5.78
     Instructions
    5.66
    Instructions
    5.47
     directions
    5.31
     instruction
    5.03
     INSTRUCTIONS
    4.59
     instrucciones
    4.53
    INSTRUCTIONS
    4.31
    directions
    4.13
    Activations Density 0.115%

    No Known Activations