© 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. 22-GEMMASCOPE-RES-131K
    7. 73262
    Prev
    Next
    INDEX
    Explanations

    TODO / instructions

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

    This neuron detects “TODO”‐style annotations in code comments, marking places where tasks or reminders are noted.

    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
    slightly
    -1.25
     bizarre
    -1.23
    僰
    -1.23
     Dinas
    -1.21
     apporter
    -1.17
    Kons
    -1.16
    Bibliografie
    -1.16
     certamente
    -1.15
     sincero
    -1.15
    creating
    -1.13
    POSITIVE LOGITS
     from
    1.96
     should
    1.84
     more
    1.82
     could
    1.78
     this
    1.74
     with
    1.66
     or
    1.60
     perhaps
    1.55
     other
    1.50
    !!!!!
    1.50
    Activations Density 0.018%

    No Known Activations