© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31886
    Prev
    Next
    INDEX
    Explanations

    names, technical terms, headers

    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
    JScrollPane
    -1.12
    scrolling
    -1.04
     scrolling
    -1.02
     scroll
    -0.93
    ScrollView
    -0.87
     zooming
    -0.86
     scrolled
    -0.84
    scroll
    -0.82
     scrolls
    -0.81
    Citizen
    -0.78
    POSITIVE LOGITS
     Halb
    0.75
     Statistik
    0.73
    ulturen
    0.72
    อยาก
    0.71
     Breite
    0.71
    Ignition
    0.70
     تونس
    0.70
     susceptibility
    0.69
    Median
    0.68
     influencers
    0.68
    Activations Density 0.003%

    No Known Activations