© 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. 40002
    Prev
    Next
    INDEX
    Explanations

    new version or upgrade

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

    The neuron fires strongly on words that denote transferring or migrating something (e.g. copying, moving, reinstalling, exporting) between locations.

    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
    municipi
    -1.07
     наличие
    -1.00
     occasional
    -1.00
     τοῦ
    -1.00
     wysokiej
    -0.99
     neither
    -0.98
     utilizada
    -0.96
     play
    -0.94
    orle
    -0.94
    τως
    -0.94
    POSITIVE LOGITS
     new
    3.20
    新的
    2.19
    new
    2.19
    ใหม่
    1.99
     새로운
    1.98
     nieuwe
    1.91
    新しい
    1.84
     neuen
    1.84
     νέ
    1.80
     nuevas
    1.78
    Activations Density 0.118%

    No Known Activations