© 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. 65855
    Prev
    Next
    INDEX
    Explanations

    momentum and energy conservation

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

    This neuron fires on occurrences of “momentum” (especially in mathematical or operator contexts, e.g. LaTeX‐style momentum operator notation).

    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
    cC
    -0.81
    àu
    -0.75
    kapp
    -0.75
    совой
    -0.71
    mrb
    -0.69
    bB
    -0.69
    nós
    -0.69
    mesg
    -0.69
    CDD
    -0.69
     élus
    -0.69
    POSITIVE LOGITS
     momentum
    2.58
    momentum
    2.09
     momenta
    1.92
    Momentum
    1.91
     Momentum
    1.90
     impulse
    1.63
     Impulse
    1.41
     impulses
    1.34
     impulso
    1.28
    Impulse
    1.28
    Activations Density 0.015%

    No Known Activations