© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12576
    Prev
    Next
    INDEX
    Explanations

    public followed by declarations

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

    The neuron activates on occurrences of the Java keyword “public,” i.e. public declarations.

    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
     annons
    -1.52
    
    -1.45
    
    -1.44
    儛
    -1.34
     programmet
    -1.33
     LYON
    -1.32
     NUEVO
    -1.32
     menyen
    -1.31
     HARVARD
    -1.30
     DÍA
    -1.30
    POSITIVE LOGITS
     what
    1.69
     how
    1.50
     such
    1.49
    ,
    1.48
     will
    1.45
     (
    1.45
    </b>
    1.38
    –
    1.36
    …
    1.34
    —
    1.25
    Activations Density 0.002%

    No Known Activations