© 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. 111010
    Prev
    Next
    INDEX
    Explanations

    per time unit

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

    The neuron fires on occurrences of the word “per,” i.e. per-unit expressions indicating rates or measurements.

    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
     pretende
    -1.59
    肺炎
    -1.55
    蟜
    -1.47
    以来
    -1.41
    萏
    -1.40
    雀
    -1.38
     alleen
    -1.36
     “[
    -1.31
    </h2>
    -1.30
    地形
    -1.29
    POSITIVE LOGITS
    わずか
    1.64
    过年
    1.55
    ⤹
    1.45
    绚
    1.43
    ꗃ
    1.42
    我来
    1.41
    买的
    1.38
     verkau
    1.38
    还不错
    1.38
    うちの
    1.36
    Activations Density 0.014%

    No Known Activations