© 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. 30279
    Prev
    Next
    INDEX
    Explanations

    legal and event-related phrases

    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
     Whilst
    -1.48
     whilst
    -1.42
     our
    -1.40
    Whilst
    -1.16
     we
    -1.14
     etc
    -1.12
     vielleicht
    -1.08
     např
    -1.03
     ایشان
    -1.03
     thru
    -1.03
    POSITIVE LOGITS
     
    1.22
    法國
    1.08
    昨天
    1.06
    雖然
    1.02
    科學
    1.02
     yesterday
    0.95
    汉
    0.94
    东西
    0.94
    虽然
    0.94
    ַּ
    0.93
    Activations Density 0.010%

    No Known Activations