© 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. 112203
    Prev
    Next
    INDEX
    Explanations

    potent substances or actions

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

    This neuron specifically responds to the adjective “potent.”

    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
    幛
    -2.55
    rs
    -2.52
     ´
    -2.50
     ་
    -2.41
    </i>
    -2.38
    on
    -2.30
    ra
    -2.27
    ch
    -2.27
     cliquer
    -2.25
     espectaculares
    -2.23
    POSITIVE LOGITS
    0
    2.69
    其
    2.34
     BRARY
    2.16
    Surprisingly
    2.16
    他的
    2.14
    鋮
    2.14
    </sup>
    2.11
     Those
    2.03
     не
    2.02
     один
    2.00
    Activations Density 0.009%

    No Known Activations