© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117817
    Prev
    Next
    INDEX
    Explanations

    leader or official title

    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
     elves
    -0.94
    ύπ
    -0.79
    byl
    -0.79
    ünstig
    -0.76
     środow
    -0.76
    chantment
    -0.74
     зимние
    -0.74
    tadora
    -0.74
    olv
    -0.74
    tifikat
    -0.73
    POSITIVE LOGITS
     leader
    1.47
     ruler
    1.16
     boss
    1.13
     leaders
    0.98
     monarch
    0.98
     politician
    0.91
    Глава
    0.90
     jurist
    0.89
    leader
    0.88
    ദ്
    0.87
    Activations Density 0.023%

    No Known Activations