© 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. 10-GEMMASCOPE-RES-131K
    7. 87412
    Prev
    Next
    INDEX
    Explanations

    Wyoming, AsString, WF

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

    This neuron fires specifically on the two‐letter uppercase sequence “WF.”

    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
    ."
    -3.02
    इटम
    -2.56
    ]
    -2.53
     "
    -2.50
    {
    -2.44
    摇了
    -2.36
     offizielle
    -2.22
    }'
    -2.22
    )'
    -2.14
     bekannte
    -2.13
    POSITIVE LOGITS
    s
    4.34
    <i>
    2.61
    u
    2.59
     –
    2.55
    o
    2.52
     함께
    2.45
                
    2.39
    g
    2.31
    ého
    2.27
    The
    2.25
    Activations Density 0.001%

    No Known Activations