© 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. 101938
    Prev
    Next
    INDEX
    Explanations

    data mismatch

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

    The neuron fires strongly whenever it encounters the word “mismatch,” regardless of context.

    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
     現貨
    -2.56
    廰
    -2.44
     sorgfäl
    -2.38
    簠
    -2.36
    美国的
    -2.33
     akin
    -2.31
     praktischen
    -2.30
    ⦾
    -2.28
    饜
    -2.23
    mpagne
    -2.22
    POSITIVE LOGITS
    d
    3.28
    e
    2.55
    s
    2.52
     &
    2.31
    ’
    2.30
    X
    2.27
    </
    2.13
    的很
    2.13
    </h1>
    2.06
    2
    2.05
    Activations Density 0.004%

    No Known Activations