© 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. 83603
    Prev
    Next
    INDEX
    Explanations

    human countries

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

    The neuron strongly activates on very common function words (e.g. pronouns like “I/I'm,” articles like “the,” conjunctions like “or,” prepositions like “in,” etc.).

    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
     ご飯
    -0.83
     Mexiko
    -0.80
     ketahui
    -0.78
     upgraded
    -0.77
     Meksiku
    -0.76
    ஂ
    -0.76
    世纪
    -0.75
    المنا
    -0.75
    燜
    -0.74
     comun
    -0.73
    POSITIVE LOGITS
     human
    1.74
     Human
    1.63
     HUMAN
    1.61
    Human
    1.57
    human
    1.51
     Humans
    1.48
    HUMAN
    1.45
    Humans
    1.44
     humans
    1.32
    humans
    1.17
    Activations Density 0.031%

    No Known Activations