© 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. 95638
    Prev
    Next
    INDEX
    Explanations

    nouns followed by who/that/where

    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
     their
    -1.85
     it
    -1.62
     numerosas
    -1.48
     something
    -1.41
     cominci
    -1.33
     two
    -1.30
     numerosos
    -1.27
    。
    -1.26
     verbessert
    -1.19
     attravers
    -1.19
    POSITIVE LOGITS
     that
    3.47
     who
    2.89
     που
    2.31
     which
    2.20
     که
    2.00
     whose
    1.97
    ที่
    1.95
     которая
    1.88
    が
    1.74
    whose
    1.70
    Activations Density 0.092%

    No Known Activations