© 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. 38087
    Prev
    Next
    INDEX
    Explanations

    organization's mission

    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
    Viitteet
    -1.00
    zepte
    -0.89
    oping
    -0.80
    öv
    -0.79
    iteritems
    -0.76
     decy
    -0.75
    etted
    -0.75
     حج
    -0.75
     referencia
    -0.74
     berry
    -0.73
    POSITIVE LOGITS
     mission
    5.09
    mission
    3.50
    Mission
    3.13
     misión
    3.05
     Mission
    3.02
     missions
    2.95
     mandate
    2.91
    MISSION
    2.64
     MISSION
    2.63
    使命
    2.48
    Activations Density 0.066%

    No Known Activations