© 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. 22-GEMMASCOPE-RES-131K
    7. 13929
    Prev
    Next
    INDEX
    Explanations

    work with

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

    The neuron strongly activates on occurrences of the verb “work” (including its inflected forms like “working” and “works”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    錞
    -2.27
    ༈
    -1.96
    梣
    -1.95
    ⩴
    -1.95
     tenham
    -1.85
    鲵
    -1.83
     corredor
    -1.80
    ኧ
    -1.76
    ⊺
    -1.76
     לאחר
    -1.76
    POSITIVE LOGITS
     to
    1.97
    If
    1.96
     Any
    1.95
    In
    1.95
     Our
    1.91
     sogenannten
    1.91
     ethic
    1.91
    ?”
    1.89
    ated
    1.88
     out
    1.84
    Activations Density 0.067%

    No Known Activations