© 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. 128085
    Prev
    Next
    INDEX
    Explanations

    smarter decisions, smarter child, SmarterTravel, Dreaming

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

    The neuron activates on occurrences of the comparative adjective “smarter.”

    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
     enkelte
    -2.25
     शुर
    -2.13
     peculiarity
    -2.08
    Municipio
    -2.02
     と
    -2.00
     überrascht
    -2.00
     komunikasi
    -1.99
     proposées
    -1.98
     abomination
    -1.97
    ！！！！
    -1.96
    POSITIVE LOGITS
    .
    3.59
    m
    2.61
     about
    2.47
     they
    2.30
    臯
    2.28
    踯
    2.27
    圌
    2.25
     him
    2.23
     котором
    2.22
    k
    2.19
    Activations Density 0.004%

    No Known Activations