© 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. 105343
    Prev
    Next
    INDEX
    Explanations

    Got followed by a word

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

    The neuron is specifically detecting occurrences of the word “got.”

    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
    笕
    -2.72
    ஂ
    -2.59
    ﮨ
    -2.44
     nye
    -2.44
    </h5>
    -2.42
    婳
    -2.36
    nextProps
    -2.33
    ﮦ
    -2.33
    ſam
    -2.31
    ⵌ
    -2.30
    POSITIVE LOGITS
    ’
    3.55
     However
    2.72
    ’;
    2.70
    '
    2.64
    ’,
    2.55
    .,
    2.44
     Conversely
    2.42
    2
    2.41
    in
    2.34
     Furthermore
    2.31
    Activations Density 0.010%

    No Known Activations