© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2497
    Prev
    Next
    INDEX
    Explanations

    center alignment

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

    The neuron fires on occurrences of the word “center” (e.g. alignment or centering attributes like center, centerHorizontal, center_vertical) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     shortcomings
    -1.05
    uurs
    -0.98
    CASH
    -0.98
    MONEY
    -0.98
    𓁹
    -0.97
     familiares
    -0.94
    ✹
    -0.94
    なのでしょう
    -0.92
     chains
    -0.91
     echte
    -0.91
    POSITIVE LOGITS
    center
    1.35
    most
    1.13
     centers
    1.08
    on
    1.08
     centro
    1.08
    pieces
    1.05
     тяже
    1.02
     CEN
    1.02
    centers
    1.02
    to
    1.00
    Activations Density 0.017%

    No Known Activations