© 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. 10-GEMMASCOPE-RES-131K
    4. 130936
    Prev
    Next
    INDEX
    Explanations

    up

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

    The neuron primarily fires on the particle “up” (and to a lesser extent “down”) when used as a directional or intensifying particle in phrasal constructions.

    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
    どのように
    -1.74
     sufficient
    -1.62
    どうやって
    -1.55
    美しく
    -1.50
    </b>
    -1.50
    完成です
    -1.50
     "
    -1.47
    --"
    -1.46
    -
    -1.43
    釙
    -1.40
    POSITIVE LOGITS
     Üniversitesi
    1.54
    桖
    1.49
    ++];
    1.48
    ṇa
    1.45
    ",@"
    1.45
    水
    1.45
     laguna
    1.43
     misalnya
    1.42
    的气息
    1.42
    \]
    1.41
    Activations Density 0.061%

    No Known Activations