© 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. 34-GEMMASCOPE-RES-131K
    7. 91683
    Prev
    Next
    INDEX
    Explanations

    there's

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

    The neuron strongly activates on existential “there’s”/“there are” constructions (sentences beginning with “there is/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_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
    ípio
    -1.02
    rfan
    -0.99
    ilirsiniz
    -0.97
     quelconque
    -0.97
    +"_
    -0.95
    alucía
    -0.94
    zzet
    -0.93
     pues
    -0.92
    +":
    -0.92
     какое
    -0.91
    POSITIVE LOGITS
     no
    1.77
     so
    1.70
     something
    1.62
     only
    1.56
     nothing
    1.48
     one
    1.43
     this
    1.36
     certainly
    1.31
     your
    1.21
     that
    1.15
    Activations Density 0.034%

    No Known Activations