© 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. 34-GEMMASCOPE-RES-131K
    7. 1514
    Prev
    Next
    INDEX
    Explanations

    'be' or questions about existence

    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
     is
    -3.00
     was
    -2.36
     has
    -1.71
     didn
    -1.48
     wasn
    -1.31
     had
    -1.28
    ᗨ
    -1.26
     hasn
    -1.25
     would
    -1.24
     BERNAMA
    -1.23
    POSITIVE LOGITS
     be
    4.97
     être
    2.20
     være
    2.13
    être
    1.90
     essere
    1.84
     have
    1.76
     быть
    1.75
     become
    1.74
     not
    1.73
    be
    1.68
    Activations Density 0.151%

    No Known Activations