© 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. 34555
    Prev
    Next
    INDEX
    Explanations

    foreign possessives and 'such'

    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
     engraçadas
    -1.11
     Menschheit
    -1.08
    orcid
    -1.03
     nien
    -0.99
    鹀
    -0.99
     zwarte
    -0.98
    arne
    -0.96
     страх
    -0.94
     mía
    -0.93
     қа
    -0.93
    POSITIVE LOGITS
     your
    1.80
     of
    1.55
     this
    1.31
     such
    1.30
    your
    1.04
     такое
    1.02
    如此
    1.02
     vaš
    0.98
     you
    0.96
     ilyen
    0.93
    Activations Density 0.002%

    No Known Activations