© 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. 34-GEMMASCOPE-RES-131K
    7. 3109
    Prev
    Next
    INDEX
    Explanations

    related to services, events, or transactions

    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
     of
    -0.96
    ซึ่ง
    -0.94
    partie
    -0.93
    wrote
    -0.91
    determined
    -0.90
    threw
    -0.88
     Determined
    -0.88
    gave
    -0.88
    began
    -0.86
    govern
    -0.85
    POSITIVE LOGITS
     encountered
    1.64
     undertaken
    1.56
     visited
    1.41
     chosen
    1.30
     received
    1.30
     purchased
    1.27
     offered
    1.23
     deployed
    1.23
     consulted
    1.17
     submitted
    1.16
    Activations Density 0.215%

    No Known Activations