© 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. 35840
    Prev
    Next
    INDEX
    Explanations

    class names

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

    The neuron is specialized to spot code annotations and structural markers (e.g. “@Bean”, “@Configuration”, the “public class … {” and indentation) in source files.

    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
     mochilas
    -1.06
    Ār
    -1.02
    indahan
    -1.00
     protocolos
    -0.99
     mangá
    -0.96
    levis
    -0.96
    capo
    -0.96
     motocicletas
    -0.96
     olvidar
    -0.95
     enfrentar
    -0.94
    POSITIVE LOGITS
    ken
    1.04
     принтом
    1.02
    а
    1.01
     nke
    0.98
    ји
    0.98
    omers
    0.98
     리
    0.93
    ◽
    0.93
    }_{
    0.93
    athi
    0.93
    Activations Density 0.003%

    No Known Activations