© 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. 34-GEMMASCOPE-RES-131K
    7. 107150
    Prev
    Next
    INDEX
    Explanations

    dynamic time

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

    The neuron fires on occurrences of the word “dynamic” (especially in technical/algorithmic phrases like “dynamic programming” or “dynamic time warping”).

    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
     Metabolic
    -0.81
    لكتر
    -0.72
    Unic
    -0.69
    hedrals
    -0.68
    icode
    -0.68
    hb
    -0.66
    Diet
    -0.66
    HB
    -0.66
    μβρίου
    -0.66
    iology
    -0.65
    POSITIVE LOGITS
     DP
    2.84
    dp
    2.64
     dp
    2.63
     dynamic
    2.58
    DP
    2.50
     Dynamic
    2.31
    Dynamic
    2.27
    dynamic
    2.14
     динами
    1.96
    动态
    1.88
    Activations Density 0.051%

    No Known Activations