© 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. 22-GEMMASCOPE-RES-131K
    7. 28124
    Prev
    Next
    INDEX
    Explanations

    individual or specific circumstances

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

    The neuron flags words that denote individual specificity or uniqueness (e.g. “each,” “unique,” “particular”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    plers
    -0.98
     cucharadas
    -0.88
    klas
    -0.88
    トル
    -0.88
     goles
    -0.87
     heads
    -0.87
    camisetas
    -0.85
    𝒆
    -0.84
     slaves
    -0.83
     ƒ
    -0.83
    POSITIVE LOGITS
     specific
    2.05
     each
    1.95
     unique
    1.94
     конкре
    1.92
     individual
    1.75
     every
    1.73
     particular
    1.70
    specific
    1.70
    每一个
    1.59
    unique
    1.51
    Activations Density 0.068%

    No Known Activations