© 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. 117764
    Prev
    Next
    INDEX
    Explanations

    idiomatic expressions and foreign words

    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
     really
    -1.02
     грома
    -0.84
    ściu
    -0.83
     rather
    -0.81
     onely
    -0.77
     خیلی
    -0.75
     malu
    -0.75
     only
    -0.75
     hygge
    -0.75
     big
    -0.75
    POSITIVE LOGITS
     Herausforderung
    0.94
     στρα
    0.92
     snee
    0.89
    🐩
    0.89
     biblical
    0.88
    給我
    0.88
     Breathing
    0.85
    jącej
    0.84
    的气息
    0.84
     remarque
    0.83
    Activations Density 0.063%

    No Known Activations