© 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. 34-GEMMASCOPE-RES-131K
    7. 93166
    Prev
    Next
    INDEX
    Explanations

    au Cap

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

    The neuron is strongly triggered by the exact two‐letter token “au,” whether as a French preposition or as the “au” in package names or abbreviations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    を
    -1.24
    が
    -0.99
    か
    -0.95
    これは
    -0.85
    、、
    -0.85
    などを
    -0.82
    と
    -0.82
    など
    -0.81
    で
    -0.81
    zige
    -0.80
    POSITIVE LOGITS
    delà
    1.06
    をします
    0.97
    事も
    0.95
     排行
    0.95
    事です
    0.94
    にします
    0.94
     pror
    0.94
    に使
    0.92
     outset
    0.91
    なのでしょう
    0.91
    Activations Density 0.002%

    No Known Activations