© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 84165
    Prev
    Next
    INDEX
    Explanations

    assembly C# code and questions

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

    This neuron spotlights section‐header keywords in code comments (e.g. “General,” “Setting,” “ComVisible,” “When,” etc.).

    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
     their
    -1.40
     its
    -1.27
     lavadora
    -1.20
    plastik
    -1.19
    örü
    -1.19
    dekat
    -1.14
     Drž
    -1.14
    ]={
    -1.13
    siębior
    -1.13
     blusa
    -1.09
    POSITIVE LOGITS
    tività
    1.07
    には
    1.05
    o
    1.02
    sohn
    1.02
    仿佛
    1.02
    спользование
    1.00
    Hilsen
    1.00
    これも
    0.99
    などは
    0.99
    lesssim
    0.99
    Activations Density 0.000%

    No Known Activations