© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 131026
    Prev
    Next
    INDEX
    Explanations

    attending school

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

    The neuron activates on mentions of “school,” especially in contexts of attending or naming a school.

    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
     любы
    -1.41
    以及
    -1.37
     inviting
    -1.33
     optionally
    -1.28
    !(
    -1.27
    喽
    -1.27
    7
    -1.26
     parado
    -1.25
    大小
    -1.25
    poietic
    -1.24
    POSITIVE LOGITS
     are
    1.44
     欣赏
    1.41
     reunião
    1.36
     entregó
    1.35
    鮰
    1.32
     Также
    1.30
     to
    1.29
     fenô
    1.26
    },
    1.25
     like
    1.25
    Activations Density 0.030%

    No Known Activations