© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40358
    Prev
    Next
    INDEX
    Explanations

    shown to

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

    The neuron detects the “has/have been shown to…” pattern used to report research findings.

    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
    3
    -1.59
     about
    -1.48
    ïlande
    -1.42
    ūros
    -1.38
    /
    -1.36
    ⚋
    -1.32
     dolu
    -1.32
    belline
    -1.30
    nós
    -1.30
    gridx
    -1.29
    POSITIVE LOGITS
     svým
    1.47
     toutefois
    1.43
     ここ
    1.34
    showed
    1.34
    楽しく
    1.34
     bezpeč
    1.34
     engraçadas
    1.33
     problémy
    1.33
     nástro
    1.30
     prostředí
    1.29
    Activations Density 0.066%

    No Known Activations