© 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. 22-GEMMASCOPE-RES-131K
    7. 68815
    Prev
    Next
    INDEX
    Explanations

    proper nouns after "The"

    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
     WENT
    -1.50
    ebly
    -1.39
     HAPPENED
    -1.38
     wybrać
    -1.31
     zobaczyć
    -1.30
     GETS
    -1.30
    ftar
    -1.29
    elts
    -1.27
    pherds
    -1.25
    ELTS
    -1.24
    POSITIVE LOGITS
     triom
    1.03
    IFYING
    0.98
    lardan
    0.96
     lourdes
    0.96
     jarang
    0.95
     diamant
    0.94
    Kuva
    0.94
    ecznie
    0.94
     vaar
    0.94
    fır
    0.93
    Activations Density 0.060%

    No Known Activations