© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38910
    Prev
    Next
    INDEX
    Explanations

    modal verbs and "I"

    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_22/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
    などなど
    -1.07
     mélange
    -1.06
     exercices
    -1.02
     lez
    -1.02
     quidem
    -1.00
     vada
    -0.99
     dessutom
    -0.98
     krab
    -0.98
    なぜか
    -0.97
     bahagia
    -0.97
    POSITIVE LOGITS
     would
    2.14
     Would
    1.35
    would
    1.25
     could
    1.24
     I
    1.11
     people
    1.09
     others
    1.09
     Could
    1.09
     earlier
    1.08
     WOULD
    1.06
    Activations Density 0.017%

    No Known Activations