© 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. 1309
    Prev
    Next
    INDEX
    Explanations

    part ways

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

    The neuron detects occurrences of “part” and its inflected forms (e.g. “parted,” “parting”) indicating separation or parting ways.

    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
    ियम
    -0.85
    direct
    -0.84
    きっと
    -0.79
    תוך
    -0.78
    RemoteException
    -0.78
     trib
    -0.77
    mira
    -0.77
     vider
    -0.76
     oogen
    -0.75
     BALANCE
    -0.74
    POSITIVE LOGITS
     ways
    2.09
     way
    1.28
     Ways
    1.23
    Ways
    1.16
    ways
    1.13
     with
    1.08
     from
    1.02
     WAYS
    0.99
     company
    0.98
     paths
    0.98
    Activations Density 0.011%

    No Known Activations