© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 68956
    Prev
    Next
    INDEX
    Explanations

    others' possessive construction

    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_10/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
    derdag
    -1.48
    }}>
    -1.29
    ""
    -1.29
    .
    -1.29
     \%}$
    -1.27
     твои
    -1.27
    жении
    -1.25
     praticamente
    -1.23
     každý
    -1.21
    atellite
    -1.21
    POSITIVE LOGITS
     but
    1.43
     muualla
    1.41
     käytet
    1.36
     violen
    1.30
     of
    1.29
     this
    1.27
     bemerk
    1.25
     colega
    1.24
     gustaba
    1.23
    dengar
    1.23
    Activations Density 0.018%

    No Known Activations