© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60290
    Prev
    Next
    INDEX
    Explanations

    since

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

    This neuron detects instances of the contracted auxiliary “’re” (as in “you’re,” “we’re,” etc.) where a pronoun is linked to the verb “are.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     when
    -2.61
    when
    -1.97
     as
    -1.90
    When
    -1.88
     simply
    -1.81
     cuando
    -1.78
     still
    -1.70
     can
    -1.66
     ketika
    -1.65
     quando
    -1.64
    POSITIVE LOGITS
    ícias
    1.73
    owaniem
    1.61
    reu
    1.53
    thmus
    1.48
    <bos>
    1.44
    isierung
    1.36
    asties
    1.36
    𖧵
    1.34
    givings
    1.33
     intervi
    1.31
    Activations Density 0.017%

    No Known Activations