© 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. 13607
    Prev
    Next
    INDEX
    Explanations

    public access modifier

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

    The neuron fires on occurrences of the Java visibility keyword “public” (e.g. in method 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
     充電
    -0.98
    幼稚園
    -0.97
     of
    -0.97
    Beskrivelse
    -0.91
     then
    -0.91
    家は
    -0.90
    ]="
    -0.88
     as
    -0.88
     it
    -0.87
    9
    -0.87
    POSITIVE LOGITS
    ඍ
    1.19
    acterium
    1.00
     XVI
    1.00
    -
    0.99
     australis
    0.97
     verhindert
    0.96
     spesielt
    0.96
    дово
    0.96
    /></
    0.96
     ViewHolder
    0.95
    Activations Density 0.002%

    No Known Activations