© 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. 39244
    Prev
    Next
    INDEX
    Explanations

    made way direction

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

    The neuron activates on the word “way” (often in movement-or-direction phrases like “make/made their way,” “way down,” or “way up”), spotting expressions of motion or path.

    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
    "
    -1.82
    X
    -1.82
    _
    -1.81
     climático
    -1.77
    which
    -1.72
    .
    -1.72
     following
    -1.70
    ที่มี
    -1.66
    谁能
    -1.66
    </td>
    -1.65
    POSITIVE LOGITS
     actrices
    1.98
     occuper
    1.91
     trusty
    1.88
    乆
    1.86
    ſſi
    1.82
    龗
    1.82
    絝
    1.82
    他对
    1.81
     sogar
    1.81
    ísticos
    1.80
    Activations Density 0.003%

    No Known Activations