© 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. 110768
    Prev
    Next
    INDEX
    Explanations

    contrast to

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

    The neuron detects the discourse marker “in contrast” introducing a contrasting statement.

    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
    瑒
    -2.89
    簠
    -2.83
    してくれた
    -2.55
    謌
    -2.41
    羕
    -2.34
     mesta
    -2.33
    ᨆ
    -2.33
    ſam
    -2.31
    lokal
    -2.28
    푢
    -2.28
    POSITIVE LOGITS
    ↵
    3.95
    .
    3.45
     is
    3.00
     been
    2.64
    It
    2.63
     $
    2.55
    </h4>
    2.50
    </em>
    2.42
    ...
    2.39
    ....
    2.27
    Activations Density 0.005%

    No Known Activations