© 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. 2340
    Prev
    Next
    INDEX
    Explanations

    gathering momentum

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

    The neuron strongly activates on occurrences of “momentum” (and closely related expressions of ongoing progress or drive).

    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
     ringer
    -0.88
    Bright
    -0.85
    ᾠ
    -0.84
     اذ
    -0.82
    desliz
    -0.82
     intelligente
    -0.82
    stände
    -0.79
     GMB
    -0.78
    vertre
    -0.78
     schreef
    -0.78
    POSITIVE LOGITS
     momentum
    5.94
    momentum
    4.44
    Momentum
    4.09
     Momentum
    3.95
     momenta
    2.53
     MOMENT
    2.16
    势
    1.95
     impetus
    1.91
    勢
    1.87
     impulso
    1.86
    Activations Density 0.033%

    No Known Activations