© 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. 76371
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by verb

    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
     говорит
    -1.09
    andere
    -0.99
    mbH
    -0.98
     Said
    -0.95
     இந்த
    -0.93
     Says
    -0.93
     λέ
    -0.93
     saying
    -0.93
     сказал
    -0.91
     said
    -0.91
    POSITIVE LOGITS
     suppose
    1.61
     know
    1.32
     hadn
    1.26
     supposes
    1.16
     still
    1.12
     never
    1.10
     wouldn
    1.09
     could
    1.09
     supposed
    1.09
     can
    1.09
    Activations Density 0.012%

    No Known Activations