© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 124638
    Prev
    Next
    INDEX
    Explanations

    __NOTOC__

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

    The neuron fires on the exact uppercase token “NO.”

    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
    of
    -3.31
    viembre
    -2.50
    which
    -2.38
     empfiehlt
    -2.33
    leggio
    -2.27
    <bos>
    -2.25
    不是
    -2.23
    琑
    -2.20
    CHREIB
    -2.20
    謇
    -2.09
    POSITIVE LOGITS
    𓐍
    3.00
    𖣔
    2.70
    梛
    2.61
    ſtra
    2.47
     腕
    2.33
     exceptionally
    2.17
    玏
    2.17
    脔
    2.14
    >
    2.14
    enablog
    2.14
    Activations Density 0.007%

    No Known Activations