© 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. 73431
    Prev
    Next
    INDEX
    Explanations

    backend adapters and drivers

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

    The neuron activates on code identifiers naming software components or abstractions (e.g. “Backend,” “adapter,” “Engine,” “Loader,” “Binding”).

    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
     annons
    -1.55
     netts
    -1.55
    第五
    -1.54
    áním
    -1.47
     gitt
    -1.44
     trattano
    -1.43
     nettsted
    -1.41
    Phen
    -1.35
     francese
    -1.33
     linge
    -1.33
    POSITIVE LOGITS
    ulitis
    1.57
    摁
    1.49
     you
    1.48
    了什么
    1.47
    cinoma
    1.47
    FTAR
    1.46
     EACH
    1.45
     BOTH
    1.45
    ᚔ
    1.44
    orological
    1.43
    Activations Density 0.086%

    No Known Activations