© 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. 71093
    Prev
    Next
    INDEX
    Explanations

    delirium, delimiter, deliberately's

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

    The neuron spikes on any token containing the character sequence “deli,” detecting that substring wherever it appears.

    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
    ῞
    -2.88
    </strong>
    -2.81
    鲠
    -2.72
    b
    -2.58
    </h3>
    -2.55
    迨
    -2.55
     ehemaligen
    -2.44
     Просто
    -2.44
     neuen
    -2.34
     frühen
    -2.34
    POSITIVE LOGITS
    _
    2.36
    ]
    2.27
    ()
    2.27
    >
    2.23
    🪐
    2.22
    隄
    2.20
    cję
    2.20
    ;
    2.17
    )||
    2.16
    他没有
    2.08
    Activations Density 0.005%

    No Known Activations