© 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. 42322
    Prev
    Next
    INDEX
    Explanations

    MOLLY C. DWYER

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

    The neuron does not reliably activate on any text patterns—it remains effectively inactive.

    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
    饪
    -3.67
    which
    -3.23
    寕
    -3.14
    ᐕ
    -2.88
    CHREIB
    -2.73
    A
    -2.70
    赑
    -2.58
    罴
    -2.52
    得好
    -2.48
    lossians
    -2.47
    POSITIVE LOGITS
    觔
    2.53
     odeur
    2.44
    ли
    2.44
     expérience
    2.34
    嫋
    2.22
    婓
    2.14
     amitié
    2.13
    Nazionale
    2.11
    餮
    2.11
    们的
    2.02
    Activations Density 0.005%

    No Known Activations