© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39811
    Prev
    Next
    INDEX
    Explanations

    actual instances of things

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

    The neuron strongly activates on occurrences of the word “real.”

    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
    Lähde
    -1.94
    走吧
    -1.79
     editors
    -1.68
    \
    -1.55
    ización
    -1.53
    joven
    -1.52
     Then
    -1.52
     zeer
    -1.50
    més
    -1.48
     детьми
    -1.46
    POSITIVE LOGITS
     magnético
    1.71
    最後まで
    1.66
    libft
    1.63
    Ironically
    1.62
    ↵
    1.62
    几个月
    1.60
    λές
    1.58
    auxite
    1.58
     which
    1.56
     tatsächlich
    1.56
    Activations Density 0.081%

    No Known Activations