© 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. 90535
    Prev
    Next
    INDEX
    Explanations

    that's followed by a detail

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

    The neuron strongly activates on the apostrophe-s (“’s”) token, i.e. contractions or possessive endings.

    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
     constater
    -1.17
     этого
    -1.15
     dette
    -1.09
     qualquer
    -1.09
     этом
    -1.09
     طرق
    -1.06
     этой
    -1.05
    อื่น
    -1.05
    aning
    -1.05
    corrhi
    -1.04
    POSITIVE LOGITS
     what
    2.08
     why
    1.88
     how
    1.77
     because
    1.72
     right
    1.65
     not
    1.58
     where
    1.43
     when
    1.39
     one
    1.31
     if
    1.26
    Activations Density 0.022%

    No Known Activations