© 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. 7023
    Prev
    Next
    INDEX
    Explanations

    setting limits

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

    The neuron fires on occurrences of the word “limit,” especially when it appears as a heading or key term (often in question titles or SQL clauses).

    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
     triump
    -0.94
     標
    -0.93
    knitted
    -0.91
    庒
    -0.91
     Knew
    -0.90
    阚
    -0.89
    Calendario
    -0.89
    Nen
    -0.89
    選舉
    -0.88
     malattia
    -0.87
    POSITIVE LOGITS
    ations
    1.30
    ting
    1.17
    less
    1.14
    ted
    1.11
    lessly
    1.10
    ers
    1.05
    ation
    1.05
    т
    1.02
    iting
    1.02
    aciones
    1.01
    Activations Density 0.029%

    No Known Activations