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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9106
    Prev
    Next
    INDEX
    Explanations

    NaCl, Mets, Knicks

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

    The neuron fires strongly on occurrences of “Mets,” i.e. references to the New York Mets baseball team.

    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
    e
    -4.16
    i
    -3.33
    ’
    -3.23
    _{
    -2.91
    u
    -2.89
    <td>
    -2.78
    0
    -2.64
    */
    -2.61
    焄
    -2.55
    。
    -2.52
    POSITIVE LOGITS
     selben
    2.50
     If
    2.42
    ޚ
    2.36
    もや
    2.34
    骝
    2.30
    釙
    2.23
     glisser
    2.20
    😸
    2.19
     we
    2.14
    有一定
    2.14
    Activations Density 0.004%

    No Known Activations