© 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. 65929
    Prev
    Next
    INDEX
    Explanations

    words beginning with es

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

    The neuron strongly activates on occurrences of the substring “Es” (e.g. in “Escherichia,” “esophageal,” “Es” itself).

    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
    犼
    -3.61
    their
    -3.41
    豋
    -3.16
    饪
    -3.09
    髕
    -3.09
     eds
    -3.03
    ſſen
    -3.02
    琑
    -3.00
    the
    -3.00
     ミニ
    -2.97
    POSITIVE LOGITS
    *
    3.38
     This
    2.89
     Es
    2.84
     There
    2.73
     While
    2.73
     decadent
    2.69
     angry
    2.56
    <
    2.56
    {
    2.56
     It
    2.55
    Activations Density 0.016%

    No Known Activations