© 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. 34-GEMMASCOPE-RES-131K
    7. 38041
    Prev
    Next
    INDEX
    Explanations

    moving closer

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

    The neuron responds to words that signal progress or movement toward a goal (e.g. “step,” “moving,” “closer,” “ahead”).

    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
    artiges
    -0.77
    logisch
    -0.75
    atoo
    -0.75
     kwiaty
    -0.74
    pstead
    -0.74
    印度
    -0.74
     défis
    -0.73
    ∊
    -0.71
    abord
    -0.71
    ckel
    -0.69
    POSITIVE LOGITS
     closer
    3.86
    closer
    2.88
     Closer
    2.67
    Closer
    2.63
     nearer
    2.61
     ближе
    2.19
     inch
    2.16
     step
    1.95
     moves
    1.88
     move
    1.86
    Activations Density 0.062%

    No Known Activations