© 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. 72922
    Prev
    Next
    INDEX
    Explanations

    execution, utilization, irradiation

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

    The neuron is a detector for Japanese‐language tokens (i.e. words or characters in Japanese text).

    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
    </h1>
    -2.33
    ”,
    -2.27
    ？」
    -2.06
     are
    -2.00
    </i>
    -1.91
     -
    -1.89
    िक
    -1.89
    )
    -1.87
    вики
    -1.86
    y
    -1.86
    POSITIVE LOGITS
    ஂ
    2.52
    ࿚
    2.31
     desenli
    2.19
    再见
    2.17
     aktiviteter
    2.14
    摃
    2.13
    豋
    2.11
    iamo
    2.03
    他们的
    2.03
    ſelves
    2.00
    Activations Density 0.004%

    No Known Activations