© 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. 22-GEMMASCOPE-RES-131K
    7. 68044
    Prev
    Next
    INDEX
    Explanations

    gradual or stepwise progression

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

    The neuron detects words and phrases that describe gradual, stepwise progression or incremental change.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ↵↵
    -0.91
    ाप्त
    -0.85
    積極的に
    -0.83
    Completo
    -0.82
    .
    -0.81
     abbraccio
    -0.81
    렀
    -0.81
     SELF
    -0.80
    produto
    -0.79
    不動産
    -0.79
    POSITIVE LOGITS
     gradually
    2.03
     gradual
    1.91
     slowly
    1.84
     постепенно
    1.57
     incremental
    1.51
    逐步
    1.47
     Slowly
    1.44
     progressivement
    1.42
    慢慢
    1.41
     Gradually
    1.38
    Activations Density 0.045%

    No Known Activations