© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108490
    Prev
    Next
    INDEX
    Explanations

    Request, Promise, External, Code, Abstract, surface

    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
     vorüber
    -1.02
    待って
    -0.93
     blijkt
    -0.93
     condominio
    -0.91
     chiusura
    -0.90
    提出的
    -0.85
    Uwagi
    -0.84
    ffins
    -0.84
     zus
    -0.84
    château
    -0.84
    POSITIVE LOGITS
    pdo
    1.04
     Abstract
    0.97
     Persian
    0.95
    sätzlich
    0.94
    rijving
    0.93
     kunne
    0.93
    PageFactory
    0.93
    зи
    0.93
     Apple
    0.90
    mixed
    0.90
    Activations Density 0.014%

    No Known Activations