© 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. 10-GEMMASCOPE-RES-131K
    7. 73878
    Prev
    Next
    INDEX
    Explanations

    group of

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

    The neuron fires strongly on occurrences of the phrase “group of.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ↵↵
    -2.05
    ↵
    -1.87
    UTELY
    -1.72
    になるので
    -1.72
     telefonu
    -1.63
    .
    -1.63
     encender
    -1.63
     häufigsten
    -1.59
     ส์
    -1.56
    The
    -1.55
    POSITIVE LOGITS
    iocene
    2.14
     of
    2.11
    」、「
    2.09
     encompassing
    1.85
    fiés
    1.78
    </strong>
    1.77
    *}$
    1.75
    
    1.68
    )।
    1.67
    "],
    1.65
    Activations Density 0.039%

    No Known Activations