© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39046
    Prev
    Next
    INDEX
    Explanations

    rapid increase, development, change, growth

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

    The neuron detects the adjective “rapid” (or adverb “rapidly”) paired with a following noun or verb, i.e. phrases signaling a fast increase, growth, or 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_10/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
    駭
    -1.43
    idopsis
    -1.41
    为什么会
    -1.38
    翻譯
    -1.38
    ellants
    -1.35
    ="'.$
    -1.35
     or
    -1.34
    entown
    -1.31
    ↵↵
    -1.30
     faded
    -1.30
    POSITIVE LOGITS
     was
    1.28
     pedimos
    1.23
     requieren
    1.23
    อื่น
    1.22
    ERIES
    1.21
     '
    1.20
    Debate
    1.19
    莚
    1.19
    ukasz
    1.19
     знаете
    1.19
    Activations Density 0.044%

    No Known Activations