© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32595
    Prev
    Next
    INDEX
    Explanations

    movement along routes

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

    The neuron fires on words that describe a path’s movement or direction—verbs like “runs,” “continues,” “flows,” “travels,” and compass points such as “north,” “south,” “east,” and “west.”

    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
    carteles
    -0.91
    ntgen
    -0.91
     key
    -0.90
     result
    -0.90
     после
    -0.88
     important
    -0.88
     valuable
    -0.86
     setup
    -0.84
     source
    -0.84
     size
    -0.84
    POSITIVE LOGITS
     along
    1.28
     to
    1.27
     across
    1.16
     continuation
    1.10
     thence
    1.04
     continúan
    1.04
    continued
    1.02
    continuing
    1.02
    continue
    1.02
     continue
    1.02
    Activations Density 0.011%

    No Known Activations