© 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. 10-GEMMASCOPE-RES-131K
    7. 793
    Prev
    Next
    INDEX
    Explanations

    bounds, constraints, robust, network components

    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
     tersebut
    -1.56
     RISERV
    -1.51
     was
    -1.38
     Empfindung
    -1.32
     tertentu
    -1.30
     bestimmte
    -1.30
    Dla
    -1.27
     również
    -1.27
    IZABETH
    -1.23
     these
    -1.17
    POSITIVE LOGITS
     or
    1.74
     todavía
    1.57
    掾
    1.53
    瞞
    1.52
    หรือ
    1.48
     celý
    1.47
     včetně
    1.47
     или
    1.46
    toContain
    1.46
     después
    1.45
    Activations Density 0.103%

    No Known Activations