© 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. 73270
    Prev
    Next
    INDEX
    Explanations

    system design and engineering

    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
    ⼰
    -1.91
    ྅
    -1.84
    鳏
    -1.80
    鶿
    -1.77
     armario
    -1.76
     célèbre
    -1.74
    uransi
    -1.72
     ſch
    -1.71
     étudi
    -1.70
     -"
    -1.70
    POSITIVE LOGITS
     systems
    2.27
    in
    2.17
    SYSTEM
    2.16
    system
    2.09
     級
    2.06
    la
    2.05
    It
    2.03
    蛧
    2.03
    f
    2.03
     SYSTEM
    2.00
    Activations Density 0.104%

    No Known Activations