© 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. 34-GEMMASCOPE-RES-131K
    7. 33482
    Prev
    Next
    INDEX
    Explanations

    reactor processes and modes

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    onai
    -0.76
     convivial
    -0.74
    ïque
    -0.74
     suelen
    -0.71
    ticides
    -0.70
    Primera
    -0.70
     命
    -0.69
    plaza
    -0.69
     Mahmoud
    -0.69
     intervenir
    -0.69
    POSITIVE LOGITS
     reactor
    3.06
     reactors
    2.53
    reactor
    2.47
     Reactor
    2.19
    Reactor
    2.11
     batch
    1.76
    react
    1.71
     REACTOR
    1.60
     реак
    1.52
    batch
    1.39
    Activations Density 0.158%

    No Known Activations