© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 104543
    Prev
    Next
    INDEX
    Explanations

    field or scope errors

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

    The neuron activates on programming identifiers—things like class or function names, namespace paths, and other code symbols (including CamelCase names and backslashes in namespaces).

    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
    Auszeichnungen
    -1.18
     lavabo
    -1.18
     olika
    -1.11
     pove
    -1.07
     desu
    -1.02
     vissa
    -1.00
    を高
    -0.99
     sociala
    -0.98
     🥰
    -0.98
     cordoba
    -0.97
    POSITIVE LOGITS
     failed
    1.31
     failure
    1.30
     caused
    1.22
     blamed
    1.02
    yó
    1.02
     fail
    1.00
     failing
    0.97
    Когда
    0.97
     blame
    0.96
    明明
    0.94
    Activations Density 0.013%

    No Known Activations