© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 11584
    Prev
    Next
    INDEX
    Explanations

    McGraw, Pasadena, interpretive, Aspen

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

    The neuron responds to low-frequency, content-bearing tokens—rare proper names, technical terms, and other uncommon words.

    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
     They
    -2.77
     frescas
    -2.45
    会の
    -2.42
     высокая
    -2.39
     informado
    -2.28
     We
    -2.28
     ビーチ
    -2.27
     alkoholu
    -2.23
    に限
    -2.22
    ではある
    -2.22
    POSITIVE LOGITS
    s
    3.47
    i
    2.91
    谖
    2.83
    )
    2.72
    5
    2.66
    玊
    2.59
    -
    2.47
    0
    2.44
    were
    2.38
    Não
    2.34
    Activations Density 0.019%

    No Known Activations