© 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. 20232
    Prev
    Next
    INDEX
    Explanations

    alignment methods, measurements, arms, layers

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

    The neuron predominantly activates on the token “alignment” (in any context or capitalization).

    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
    ines
    -2.94
    of
    -2.91
    硨
    -2.72
    みたら
    -2.67
    堪
    -2.56
     dari
    -2.56
    鶫
    -2.47
     immobili
    -2.45
    ar
    -2.42
    是
    -2.42
    POSITIVE LOGITS
    趼
    4.09
    欵
    3.22
    衎
    3.13
    Ꭳ
    2.98
    弍
    2.84
    Ꮸ
    2.83
    蛱
    2.67
    𐄁
    2.67
    鄠
    2.66
    鈇
    2.58
    Activations Density 0.003%

    No Known Activations