© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 37918
    Prev
    Next
    INDEX
    Explanations

    cheap, affordable, inexpensive

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

    The neuron fires on language describing organized programs, projects, or policy initiatives (e.g. talks of “using new treatments,” “tackle the problem,” “choice of an operating system for 17,000 PCs,” etc.).

    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
     huwa
    -0.96
    打扮
    -0.92
    istungen
    -0.89
     Hispanic
    -0.88
     wako
    -0.85
     heerlijk
    -0.84
     genommen
    -0.82
    zion
    -0.82
     libur
    -0.82
     récompenses
    -0.82
    POSITIVE LOGITS
     affordable
    1.50
     cheap
    1.48
     inexpensive
    1.45
     cheaply
    1.23
     low
    1.21
     cheapest
    1.05
     Cheap
    1.05
     affordability
    1.05
     Affordable
    1.04
     simple
    1.03
    Activations Density 0.069%

    No Known Activations