© 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. 10-GEMMASCOPE-RES-131K
    7. 110694
    Prev
    Next
    INDEX
    Explanations

    way to destinations

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

    The neuron fires on travel‐direction expressions—tokens in phrases like “way to X” or “en route to X” linking movement toward a place (often with a numeric distance).

    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
     tomando
    -1.93
     colocando
    -1.91
     mostrando
    -1.84
    ⽆
    -1.77
     alojamientos
    -1.73
     contando
    -1.67
     esperando
    -1.65
     dando
    -1.65
     ow
    -1.63
    ཽ
    -1.63
    POSITIVE LOGITS
     being
    1.87
     a
    1.84
    as
    1.76
     having
    1.74
     establishing
    1.70
    蕷
    1.70
     becoming
    1.66
    我们
    1.63
    thodox
    1.63
    ang
    1.61
    Activations Density 0.009%

    No Known Activations