© 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. 130001
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on code‐specific identifiers—especially module/package names and type/class tokens (e.g. import paths, class names, wrapper or generated symbols).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    generated protobuf or code

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     to
    -1.38
     while
    -1.29
     with
    -1.28
     for
    -1.19
     time
    -1.17
     a
    -1.08
     idea
    -1.07
     this
    -1.03
     will
    -1.03
     zudem
    -1.02
    POSITIVE LOGITS
     granit
    1.25
    椀
    1.20
     ſer
    1.18
     sirop
    1.15
     amplit
    1.14
     vann
    1.14
     cemento
    1.13
     botines
    1.12
    ⬛
    1.12
     lokal
    1.09
    Activations Density 0.021%

    No Known Activations