© 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. 35588
    Prev
    Next
    INDEX
    Explanations

    code execution or definition

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

    The neuron spotlights code- or formula-style identifiers and constants (e.g. variable names, filenames, tags, parameters, numeric literals) in technical snippets.

    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
     celé
    -0.83
    quetas
    -0.82
     enfoque
    -0.82
    mella
    -0.81
    的想法
    -0.80
    idados
    -0.80
     ocorrer
    -0.78
    urantes
    -0.77
    ASONS
    -0.76
     ngắn
    -0.76
    POSITIVE LOGITS
     these
    0.95
    U
    0.85
     what
    0.78
    </h6>
    0.77
     didat
    0.76
    """
    
    0.75
     conversa
    0.73
    myk
    0.73
    ```
    
    0.73
     one
    0.72
    Activations Density 0.052%

    No Known Activations