© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 94241
    Prev
    Next
    INDEX
    Explanations

    there followed by forms of to be

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

    The neuron is detecting the token “there” (as in existential “there”).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     a
    -0.94
     has
    -0.88
     dê
    -0.84
     cà
    -0.83
    ahas
    -0.81
     đã
    -0.80
    féle
    -0.78
    廨
    -0.78
    єте
    -0.77
    ATED
    -0.77
    POSITIVE LOGITS
     nadzie
    0.91
     no
    0.81
    nser
    0.79
     basada
    0.77
    étend
    0.77
     provided
    0.77
     recrutement
    0.77
    ’
    0.77
     состави
    0.77
     markedly
    0.76
    Activations Density 0.029%

    No Known Activations