© 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. 39552
    Prev
    Next
    INDEX
    Explanations

    com. or proper nouns followed by verbs

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

    The neuron spikes whenever it sees the three‐letter token “com” (as in domain or package 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
     informar
    -1.09
    setupUi
    -1.06
     bombas
    -1.05
     tableta
    -1.05
     palab
    -1.05
    úrate
    -1.03
     invá
    -1.02
     ModelRenderer
    -1.01
     morales
    -1.01
     índice
    -0.98
    POSITIVE LOGITS
     Сам
    1.03
     męska
    1.02
                    
    1.00
     essenziale
    0.99
    AKA
    0.98
                     
    0.96
     endow
    0.95
     czerwony
    0.93
                         
    0.92
     Enables
    0.92
    Activations Density 0.000%

    No Known Activations