© 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. 58600
    Prev
    Next
    INDEX
    Explanations

    sequence part of

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron activates strongly for the phrase "part of" when describing something as an essential or integral component of something else.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     sake
    -0.93
     impresiones
    -0.88
    なのかな
    -0.85
     least
    -0.85
    endpush
    -0.83
     regalías
    -0.81
     soldadura
    -0.81
    følgelig
    -0.81
    edì
    -0.80
    rictive
    -0.80
    POSITIVE LOGITS
     of
    3.28
     in
    1.40
     any
    1.33
     to
    1.19
     our
    1.09
     любого
    1.07
    ของ
    1.05
     many
    1.02
     every
    1.00
     của
    1.00
    Activations Density 0.023%

    No Known Activations