© 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. 22-GEMMASCOPE-RES-131K
    7. 73160
    Prev
    Next
    INDEX
    Explanations

    Python class definitions

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

    The neuron detects the declaration of an inner “Meta” class (and its ordering field) in Django model definitions.

    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
     with
    -1.46
     during
    -1.41
     to
    -1.17
     through
    -1.07
     sejumlah
    -1.05
     components
    -1.05
     During
    -1.03
    enuto
    -1.02
     other
    -1.02
     their
    -0.98
    POSITIVE LOGITS
     lesquels
    1.08
     horrible
    1.05
     extremely
    1.05
     hugely
    1.04
     dreadful
    1.01
     tremendous
    0.99
    を探す
    0.98
     terrific
    0.97
     lesquelles
    0.96
     meubles
    0.95
    Activations Density 0.001%

    No Known Activations