© 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. 32701
    Prev
    Next
    INDEX
    Explanations

    class and object properties

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

    The neuron activates strongly on uses of the “this.” keyword (object-property references) in code.

    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
     både
    -1.38
     geschenk
    -1.37
     kabát
    -1.33
     triko
    -1.30
    besos
    -1.26
     illustre
    -1.24
    ✴
    -1.24
     quatrième
    -1.24
    ĝo
    -1.22
    nuestro
    -1.21
    POSITIVE LOGITS
     is
    1.49
     currently
    1.38
     original
    1.34
     was
    1.30
     last
    1.27
     _
    1.24
    H
    1.22
     had
    1.21
     m
    1.21
     W
    1.18
    Activations Density 0.021%

    No Known Activations