© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64043
    Prev
    Next
    INDEX
    Explanations

    verb "to be" across languages

    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
     которые
    -1.34
     которое
    -1.20
     which
    -1.19
     WHICH
    -1.16
     is
    -1.16
    荭
    -1.14
    which
    -1.11
     clô
    -1.06
    それが
    -1.06
     marcha
    -1.06
    POSITIVE LOGITS
     in
    1.79
     among
    1.32
     available
    1.30
     like
    1.25
     to
    1.23
     visible
    1.20
    '
    1.14
     además
    1.13
     also
    1.12
     involved
    1.08
    Activations Density 0.006%

    No Known Activations