© 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. 10-GEMMASCOPE-RES-131K
    7. 75423
    Prev
    Next
    INDEX
    Explanations

    knowledge and education

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

    The neuron responds to terms related to education, learning, or intellectual knowledge (e.g. words about being educated or uneducated, broadening the mind, knowledge, and related concepts).

    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
     queridos
    -1.27
     the
    -1.23
    $
    -1.21
    ऽ
    -1.20
     longtemps
    -1.16
    toim
    -1.16
    {...
    -1.13
    ти
    -1.13
     anderen
    -1.13
    '`
    -1.12
    POSITIVE LOGITS
     vescovo
    1.37
     chàng
    1.37
     also
    1.36
     passenden
    1.33
     också
    1.29
    </strong>
    1.27
     тоже
    1.27
     acquired
    1.25
     acquaintance
    1.24
    時間も
    1.24
    Activations Density 0.039%

    No Known Activations