© 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. 2702
    Prev
    Next
    INDEX
    Explanations

    forms of to be

    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
     نے
    -0.95
    чак
    -0.91
     belong
    -0.91
     должны
    -0.87
    hynch
    -0.86
    🥎
    -0.84
     represents
    -0.84
     comprises
    -0.82
     estão
    -0.81
     arises
    -0.81
    POSITIVE LOGITS
     be
    1.94
     быть
    1.92
     είναι
    1.91
     être
    1.82
     is
    1.75
    être
    1.59
     бути
    1.55
     are
    1.46
     være
    1.46
    toBe
    1.44
    Activations Density 0.301%

    No Known Activations