© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57889
    Prev
    Next
    INDEX
    Explanations

    concurrency primitives

    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
    paquete
    -0.91
    empresa
    -0.82
     pourrais
    -0.80
     Öffnen
    -0.79
     optimum
    -0.79
     ausgewä
    -0.75
     zasi
    -0.75
     -
    -0.75
     April
    -0.74
    於是
    -0.74
    POSITIVE LOGITS
    RequestQueue
    1.04
    continence
    1.03
    EventQueue
    0.98
    ammlung
    0.96
    WriteBarrier
    0.94
    вления
    0.93
    MainThread
    0.91
     acces
    0.91
    ertia
    0.90
     interess
    0.89
    Activations Density 0.008%

    No Known Activations