© 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. 34-GEMMASCOPE-RES-131K
    7. 37765
    Prev
    Next
    INDEX
    Explanations

    international entities and numbers

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

    The neuron fires strongly on very common high-frequency English function words (e.g. “the,” “that”) and related grammatical tokens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     vinculado
    -1.02
     formado
    -0.96
    covid
    -0.95
     通り
    -0.92
     humane
    -0.88
     melayani
    -0.88
    CURSO
    -0.87
     semoga
    -0.86
     buscado
    -0.86
     protegido
    -0.84
    POSITIVE LOGITS
    ($
    1.11
    SOUNDBITE
    1.05
    Unfortunately
    1.01
     cependant
    0.98
    いただきます
    0.97
    但
    0.95
     Reuters
    0.93
    Já
    0.91
    印象
    0.91
     Sinh
    0.89
    Activations Density 0.004%

    No Known Activations