© 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. 22-GEMMASCOPE-RES-131K
    7. 40210
    Prev
    Next
    INDEX
    Explanations

    Eureka! Tent Company

    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_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
    hydrogenase
    -1.03
    活動を
    -0.99
     while
    -0.98
     when
    -0.93
    σουν
    -0.87
    ⿴
    -0.84
     something
    -0.84
    guió
    -0.84
    瑩
    -0.83
     since
    -0.80
    POSITIVE LOGITS
     will
    0.92
    mainly
    0.90
     refra
    0.86
     Mahindra
    0.85
    legt
    0.84
     verde
    0.84
     turtles
    0.83
     naturen
    0.83
     australis
    0.83
    躲
    0.83
    Activations Density 0.000%

    No Known Activations