© 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. 32979
    Prev
    Next
    INDEX
    Explanations

    multiple related objects

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

    The neuron strongly activates on common nouns in their plural form (i.e. words ending in “s” that denote countable items).

    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
     its
    -1.98
     itself
    -1.76
    它
    -1.58
     it
    -1.53
    the
    -1.23
     is
    -1.10
    on
    -1.09
    e
    -1.09
    着一个
    -1.09
    el
    -1.08
    POSITIVE LOGITS
     themselves
    2.05
    themselves
    1.72
     которые
    1.70
     amelyek
    1.38
     respective
    1.36
     respectivas
    1.34
    各自
    1.33
     których
    1.33
     ihnen
    1.31
    Their
    1.30
    Activations Density 0.631%

    No Known Activations