© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 20997
    Prev
    Next
    INDEX
    Explanations

    code routing and table definitions

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

    The neuron activates on Java annotation tokens (the “@…”) in code.

    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
    旆
    -1.41
    $
    -1.38
    )]
    
    -1.30
    "))
    
    -1.30
    ३
    -1.28
    )})
    -1.28
    Just
    -1.24
    いた
    -1.22
    }})
    -1.20
    Even
    -1.18
    POSITIVE LOGITS
     their
    1.73
     is
    1.44
    豋
    1.40
     thier
    1.35
     również
    1.31
     anunció
    1.31
     sessão
    1.27
    閖
    1.27
    única
    1.27
     coleção
    1.26
    Activations Density 0.001%

    No Known Activations