© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 66913
    Prev
    Next
    INDEX
    Explanations

    computer components and configuration

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

    The neuron fires on standalone technical or section‐heading keywords (single nouns) that label parts of a document—for example “materials,” “file,” “provisioning,” “handlers,” “space,” “nodes,” “disabling,” “components,” “supports,” “table,” or “function.”

    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
    зумі
    -1.03
     Romains
    -0.99
     merasa
    -0.96
     ander
    -0.89
    vateľ
    -0.88
    Виды
    -0.87
     slightest
    -0.86
     competición
    -0.84
     Autobahn
    -0.84
    #%%
    
    -0.83
    POSITIVE LOGITS
     into
    1.05
    cestry
    1.01
     is
    1.00
    nesc
    0.94
    Ner
    0.94
     évo
    0.93
    valy
    0.93
     itself
    0.93
    dotto
    0.91
    tainty
    0.90
    Activations Density 0.090%

    No Known Activations