© 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. 74684
    Prev
    Next
    INDEX
    Explanations

    over or past

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

    The neuron activates on numeric values and measurements (including numbers following words like “over”).

    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
     he
    -2.50
    ↵↵
    -2.03
    j
    -1.95
    x
    -1.89
     You
    -1.86
     –
    -1.81
    --
    -1.81
    –
    -1.75
    n
    -1.75
    of
    -1.75
    POSITIVE LOGITS
    鼉
    2.14
    ⌵
    1.91
     essentielle
    1.91
     剧照
    1.87
     événement
    1.86
    噚
    1.86
    ㍑
    1.84
     撮っ
    1.84
    actéristi
    1.83
     sprüche
    1.80
    Activations Density 0.005%

    No Known Activations