© 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. 60935
    Prev
    Next
    INDEX
    Explanations

    ae, ao followed by characters

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

    The neuron consistently fires on the character sequence “ae.”

    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
    沕
    -2.84
    ↵↵
    -2.78
    _{
    -2.75
    ],
    -2.69
    ).
    -2.69
    "));
    -2.66
    㐂
    -2.64
    咴
    -2.58
    C
    -2.52
    lossians
    -2.50
    POSITIVE LOGITS
    翃
    2.95
     be
    2.52
    en
    2.42
    щихся
    2.39
     crux
    2.33
    是有
    2.31
     Trotz
    2.30
     atteinte
    2.30
    気付
    2.28
    を行
    2.25
    Activations Density 0.005%

    No Known Activations