© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111377
    Prev
    Next
    INDEX
    Explanations

    locations and positions

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

    The neuron strongly activates on content-heavy, less frequent words—especially proper names, technical terms, and other rare or “information-rich” 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_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
     acompañado
    -1.58
     adequado
    -1.51
     against
    -1.41
    身近
    -1.40
     limitaciones
    -1.38
     nový
    -1.37
     between
    -1.36
     extremamente
    -1.34
     подойдет
    -1.34
     such
    -1.33
    POSITIVE LOGITS
     by
    1.38
     vertu
    1.20
     who
    1.16
     meisten
    1.15
     nyeri
    1.12
     their
    1.07
     which
    1.07
     Gór
    1.05
    ,:)
    1.05
     extraordin
    1.05
    Activations Density 0.068%

    No Known Activations