© 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. 34-GEMMASCOPE-RES-131K
    4. 34769
    Prev
    Next
    INDEX
    Explanations

    transaction propagation and lifecycle

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

    The neuron fires on individual listed configuration option names or allowed setting values (e.g. the “jta,” “thread,” and “managed” entries) in code‐example lists.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Dao
    -0.76
     Cunningham
    -0.75
     Gym
    -0.75
    unningham
    -0.71
     Мо
    -0.71
    moose
    -0.70
     injury
    -0.70
     gym
    -0.69
     Daw
    -0.68
    hatic
    -0.68
    POSITIVE LOGITS
     Propagation
    0.91
    REQUIRES
    0.85
    gulp
    0.85
    spreis
    0.83
     olet
    0.81
     recom
    0.79
     demarcation
    0.79
     propagation
    0.77
     demar
    0.76
    Propagation
    0.75
    Activations Density 0.011%

    No Known Activations