© 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. 60016
    Prev
    Next
    INDEX
    Explanations

    constructor parameters and declarations

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

    The neuron fires on parameter or argument identifiers when they’re being assigned to instance fields—i.e. variable names on the right‐hand side of “this.field = parameter” (especially in constructors).

    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
     nära
    -0.99
    );//
    -0.93
    someone
    -0.90
     Voyez
    -0.88
    довых
    -0.88
     Résultat
    -0.88
     évêque
    -0.86
    ");//
    -0.85
     även
    -0.85
    ➀
    -0.84
    POSITIVE LOGITS
     or
    1.05
     of
    1.00
     этого
    0.84
    ⑷
    0.83
     этому
    0.82
     acestei
    0.80
    นี้
    0.80
     svého
    0.79
     heerlijk
    0.78
    magem
    0.77
    Activations Density 0.004%

    No Known Activations