© 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. 22-GEMMASCOPE-RES-131K
    7. 71388
    Prev
    Next
    INDEX
    Explanations

    rightKatherine

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

    The neuron activates on words that serve as column headings or labels in tables (e.g. “Place,” “Driver,” “Time”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     estudian
    -0.98
    山市
    -0.86
    に加
    -0.85
     frère
    -0.84
     några
    -0.84
     entrevista
    -0.82
     лоша
    -0.81
    ticia
    -0.81
     procesos
    -0.80
     Теле
    -0.80
    POSITIVE LOGITS
    cisme
    0.88
    cticas
    0.88
     from
    0.88
     grammi
    0.86
    Ϲ
    0.84
     museu
    0.83
    Historically
    0.83
    avad
    0.83
    ాన
    0.80
    同樣
    0.78
    Activations Density 0.001%

    No Known Activations