© 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. 83142
    Prev
    Next
    INDEX
    Explanations

    speaking, asking, and relational terms

    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
     menek
    -0.97
     Może
    -0.92
     gümüş
    -0.87
     mengakui
    -0.86
     mengangg
    -0.84
    妪
    -0.84
     xào
    -0.84
     minggu
    -0.84
    📇
    -0.84
     mengucap
    -0.83
    POSITIVE LOGITS
     asks
    1.50
     says
    1.44
     said
    1.35
     asked
    1.29
     asking
    1.05
     tense
    1.02
     ask
    1.02
     recalled
    1.00
     requested
    0.92
     looks
    0.91
    Activations Density 0.003%

    No Known Activations