© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14518
    Prev
    Next
    INDEX
    Explanations

    basic methods and concepts

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

    The neuron activates on the adjective “basic,” detecting instances where a document refers to “basic” things, data, methods, insights, etc.

    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
     "
    -1.58
     continuamente
    -1.46
     BOTH
    -1.45
     particular
    -1.45
    <i>
    -1.42
    </h2>
    -1.42
    ۷
    -1.42
     The
    -1.39
    section
    -1.39
     Seen
    -1.35
    POSITIVE LOGITS
    元々
    1.62
    🛖
    1.61
    ಂಗ
    1.56
    Dữ
    1.45
    鮠
    1.45
     elegance
    1.44
    媜
    1.41
    ↵↵
    1.41
    늑
    1.39
     indifference
    1.35
    Activations Density 0.051%

    No Known Activations