© 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. 44191
    Prev
    Next
    INDEX
    Explanations

    perfect followed by context

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

    The neuron specifically activates on occurrences of the word “perfect.”

    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
    赑
    -1.98
     berücksich
    -1.82
    狨
    -1.75
    鹛
    -1.74
    }}{
    -1.73
    </h3>
    -1.62
    umerable
    -1.56
    digans
    -1.56
    これらの
    -1.55
     gekenn
    -1.55
    POSITIVE LOGITS
     categorized
    1.71
     namorado
    1.63
     попыта
    1.55
     pequ
    1.55
     newData
    1.53
    以上です
    1.52
     subje
    1.52
    無い
    1.51
    as
    1.48
     infal
    1.47
    Activations Density 0.011%

    No Known Activations