© 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. 84610
    Prev
    Next
    INDEX
    Explanations

    I feel like

    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
    覺得
    -1.22
     thấy
    -1.06
     seeming
    -1.04
    認為
    -1.03
     deemed
    -1.03
     fascinated
    -1.02
     thought
    -1.02
    看來
    -1.01
    びっくり
    -1.01
     fear
    -1.00
    POSITIVE LOGITS
     maybe
    1.20
     betrayal
    1.09
     adequately
    1.05
     cheated
    1.05
     although
    1.02
     somehow
    1.00
     constantly
    0.99
     could
    0.96
     perhaps
    0.95
     vindicated
    0.94
    Activations Density 0.023%

    No Known Activations