© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117639
    Prev
    Next
    INDEX
    Explanations

    work in progress

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

    The neuron detects mentions that the text or project is still ongoing or unfinished, i.e. “work in progress.”

    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
     espaços
    -0.77
    リーナ
    -0.72
     urgencia
    -0.71
    šené
    -0.70
    ByKey
    -0.70
    不动
    -0.68
    θρώ
    -0.66
    ába
    -0.66
     LAM
    -0.66
     Biographical
    -0.65
    POSITIVE LOGITS
     work
    3.58
     WIP
    2.86
     Work
    2.78
    Work
    2.70
    work
    2.61
    WIP
    2.34
     works
    2.31
     WORK
    2.09
     ongoing
    1.98
    WORK
    1.98
    Activations Density 0.049%

    No Known Activations