© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27861
    Prev
    Next
    INDEX
    Explanations

    technical documentation phrases

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

    The neuron detects Java annotation names.

    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
     can
    -1.33
     people
    -1.32
     produces
    -1.27
     specific
    -1.23
     seven
    -1.18
     three
    -1.18
     creates
    -1.18
    .......
    -1.16
     that
    -1.15
     Numerous
    -1.13
    POSITIVE LOGITS
     lokale
    1.22
     vaisseaux
    1.14
     maniere
    1.12
     wees
    1.10
     intrig
    1.09
    絝
    1.09
    埂
    1.08
     uſe
    1.08
     ſy
    1.07
     vermel
    1.06
    Activations Density 0.000%

    No Known Activations