© 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. 10-GEMMASCOPE-RES-131K
    7. 39660
    Prev
    Next
    INDEX
    Explanations

    aforementioned words

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

    The neuron fires on the term used to point back to something already mentioned—that is, instances of “aforementioned.”

    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
    后
    -2.58
    },
    -2.52
     {
    -2.52
    釭
    -2.42
     или
    -2.42
    )
    -2.38
    ]
    -2.34
     [
    -2.25
    </b>
    -2.20
    可以
    -2.19
    POSITIVE LOGITS
    ↵
    3.94
    G
    2.89
    跸
    2.84
    淠
    2.78
    但是在
    2.77
    
    2.73
     メニュー
    2.72
    鲧
    2.70
     概要
    2.67
    𓆏
    2.63
    Activations Density 0.008%

    No Known Activations