© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 28126
    Prev
    Next
    INDEX
    Explanations

    static final declarations

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

    This neuron fires on occurrences of “static final” field declarations (the modifiers in Java constant 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
     musíte
    -1.16
    卝
    -1.10
    優しい
    -1.10
     its
    -1.09
     sekarang
    -1.09
    aucun
    -1.06
     também
    -1.00
     sauvegarde
    -0.99
     różnych
    -0.99
    irited
    -0.98
    POSITIVE LOGITS
    	
    1.13
    😱
    1.05
    >)
    1.01
    }*/
    
    1.00
     イ
    0.99
    )})
    0.98
    ^_^
    0.97
    ::$_
    0.96
     き
    0.95
    ///</
    0.95
    Activations Density 0.001%

    No Known Activations