© 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. 22-GEMMASCOPE-RES-131K
    7. 128341
    Prev
    Next
    INDEX
    Explanations

    The neuron specifically detects occurrences of the word “Member” (in code or text).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    member references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     Ejecutivo
    -2.81
     beliebt
    -2.48
     campeones
    -2.45
    憷
    -2.45
     ciudadanos
    -2.42
    囟
    -2.42
     alrededores
    -2.41
    喾
    -2.41
    chyma
    -2.31
     incredibly
    -2.30
    POSITIVE LOGITS
    趼
    3.25
    ⢓
    3.03
    𖥧
    2.92
    グルト
    2.84
    狆
    2.80
    ⦊
    2.72
    淠
    2.67
    
    2.66
    というわけで
    2.66
     For
    2.64
    Activations Density 0.029%

    No Known Activations