© 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. 84233
    Prev
    Next
    INDEX
    Explanations

    tremendous scale or magnitude

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

    The neuron specifically activates on the adjective “tremendous,” identifying that intensifier wherever it occurs.

    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
    s
    -2.69
    埽
    -2.67
    鹛
    -2.67
    놋
    -2.59
    鯪
    -2.56
    縢
    -2.55
     ними
    -2.52
     wth
    -2.52
    胧
    -2.44
    -​
    -2.33
    POSITIVE LOGITS
    趼
    3.22
    спомина
    2.77
    衪
    2.73
    Ideally
    2.56
    Approximately
    2.55
    勍
    2.45
    ременно
    2.38
    蘩
    2.38
    Ultimately
    2.36
    椟
    2.36
    Activations Density 0.003%

    No Known Activations