© 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. 65043
    Prev
    Next
    INDEX
    Explanations

    SPDX-License-Identifier

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

    The neuron fires on SPDX license identifiers (and related license-comment markers) in source‐file headers.

    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
    </h2>
    -2.48
    </sup>
    -2.08
    </strong>
    -2.05
    </h4>
    -1.97
     irgend
    -1.87
    ↵
    -1.83
    </em>
    -1.82
    r
    -1.80
     spezi
    -1.79
    醅
    -1.77
    POSITIVE LOGITS
    ющих
    1.72
    like
    1.63
     divisa
    1.62
    digung
    1.59
    ÍSTICAS
    1.57
     が
    1.57
     in
    1.56
    峩
    1.55
    ⃙
    1.55
    BIÉN
    1.54
    Activations Density 0.005%

    No Known Activations