© 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. 100829
    Prev
    Next
    INDEX
    Explanations

    Under Armour, class, weight,neath, price, age

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

    The neuron activates on the token “under,” particularly when it appears as a modifier before numbers or nouns.

    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
    '
    -3.50
    and
    -2.58
    手动
    -2.47
    餮
    -2.42
     แต่
    -2.39
    e
    -2.38
    every
    -2.36
    桄
    -2.34
    栳
    -2.31
    饽
    -2.28
    POSITIVE LOGITS
    The
    3.13
    很是
    2.98
    ︲
    2.92
    随即
    2.91
     WITH
    2.69
    歃
    2.66
    芣
    2.64
    It
    2.64
     alemán
    2.59
    는
    2.56
    Activations Density 0.080%

    No Known Activations