© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 27938
    Prev
    Next
    INDEX
    Explanations

    side to, last href

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

    The neuron strongly activates on technical‐specification or requirements language (e.g. layout, minimum, size, requirements, clearance) found in headings or instruction titles.

    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
     vacunas
    -1.07
     ventajas
    -1.00
     caza
    -0.95
    $)
    -0.95
     beneficios
    -0.91
     trouvait
    -0.91
     нынеш
    -0.90
    »),
    -0.89
     моих
    -0.86
     מִ
    -0.86
    POSITIVE LOGITS
    日常
    0.91
    чну
    0.90
     meliputi
    0.90
     أيض
    0.87
    According
    0.87
     및
    0.86
    can
    0.85
     physiologic
    0.84
    主要
    0.83
    orme
    0.81
    Activations Density 0.023%

    No Known Activations