© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 12741
    Prev
    Next
    INDEX
    Explanations

    optimal control problems and parameters

    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_10/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
     aprire
    -1.38
    看見
    -1.26
    することができます
    -1.23
    取决
    -1.17
     Recognizing
    -1.13
     ανά
    -1.12
    則是
    -1.10
    非常的
    -1.10
     Wherefore
    -1.09
     spéciale
    -1.07
    POSITIVE LOGITS
     either
    1.27
    örté
    1.26
     również
    1.23
     myös
    1.20
     now
    1.20
    lanmış
    1.18
     already
    1.16
    
    1.15
     recently
    1.15
     também
    1.13
    Activations Density 0.019%

    No Known Activations