© 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. 47692
    Prev
    Next
    INDEX
    Explanations

    places of education

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

    The neuron strongly activates on section or article titles—especially “Rise and Fall”–style headings.

    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
    蕯
    -1.38
     kvůli
    -1.31
     pases
    -1.27
     [&
    -1.27
     AspNetCore
    -1.26
    梣
    -1.23
     proprietario
    -1.23
    ἄ
    -1.20
     recomand
    -1.20
    szön
    -1.20
    POSITIVE LOGITS
    ,
    1.86
    In
    1.43
    гряз
    1.41
    zulegen
    1.38
    ٦
    1.36
    zubauen
    1.31
    président
    1.29
    each
    1.28
     trois
    1.27
     éxito
    1.26
    Activations Density 0.079%

    No Known Activations