© 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. 91019
    Prev
    Next
    INDEX
    Explanations

    depends on

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

    The neuron strongly activates on common function words and pronouns (e.g., “you,” “it,” “this,” “is,” “for,” “depends”) rather than content words.

    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
     judiciales
    -0.84
    ̛
    -0.82
    gisayar
    -0.82
     Mitteln
    -0.81
    ")}
    -0.80
    Parece
    -0.77
    rinha
    -0.76
    愍
    -0.75
    Sooo
    -0.75
    ')}
    -0.75
    POSITIVE LOGITS
     depends
    7.84
     Depends
    5.69
     depend
    5.69
    depends
    5.66
    Depends
    5.50
     зависит
    5.19
     depended
    5.03
     dépend
    4.88
     depende
    4.78
     depending
    4.59
    Activations Density 0.161%

    No Known Activations