© 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. 34-GEMMASCOPE-RES-131K
    7. 54105
    Prev
    Next
    INDEX
    Explanations

    lives and moves

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

    The neuron strongly activates on factual “metadata” tokens—proper names, place names, and numbers—i.e. the little bits of concrete identifying information in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    SOUNDBITE
    -0.76
    Mejores
    -0.73
    Artículos
    -0.72
    Manger
    -0.69
    ensible
    -0.68
     experto
    -0.68
    Pacote
    -0.67
    つた
    -0.67
    Meli
    -0.66
    רת
    -0.66
    POSITIVE LOGITS
     split
    4.66
     divided
    4.34
    split
    3.97
    Split
    3.81
     divide
    3.72
     Split
    3.58
     splitting
    3.50
     divides
    3.41
     splits
    3.41
    divided
    3.23
    Activations Density 0.106%

    No Known Activations