© 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. 9430
    Prev
    Next
    INDEX
    Explanations

    HPC, Nish, locom, NSC

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

    The neuron activates whenever it sees the exact uppercase acronym “HPC.”

    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
     Öffnen
    -2.52
     istimewa
    -2.52
     ofreci
    -2.44
     terkenal
    -2.42
     撮っ
    -2.38
     kekinian
    -2.36
     pantalón
    -2.34
    姈
    -2.34
    ANCE
    -2.34
     ظهور
    -2.33
    POSITIVE LOGITS
    al
    2.66
    ஂ
    2.61
    这个
    2.56
    这
    2.53
    這一
    2.47
     моя
    2.41
    or
    2.41
    這個
    2.36
    或
    2.36
    ︲
    2.31
    Activations Density 0.082%

    No Known Activations