© 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. 10-GEMMASCOPE-RES-131K
    7. 13924
    Prev
    Next
    INDEX
    Explanations

    Go imports and libraries

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

    This neuron detects segments of Go import path strings—especially Kubernetes-related “k8s.io/…” package paths.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    </b>
    -1.58
    r
    -1.56
     From
    -1.54
    ?
    -1.43
     This
    -1.43
     so
    -1.40
     månader
    -1.38
    mschrijving
    -1.38
     make
    -1.37
     förra
    -1.37
    POSITIVE LOGITS
    donde
    1.53
     které
    1.47
     ofrecen
    1.46
    </h3>
    1.46
     Перейти
    1.44
     aluguel
    1.43
     które
    1.43
    éről
    1.41
     jednej
    1.41
     to
    1.37
    Activations Density 0.031%

    No Known Activations