© 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. 120104
    Prev
    Next
    INDEX
    Explanations

    up or down

    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
    7
    -1.55
    The
    -1.38
     gearbeitet
    -1.27
    3
    -1.23
    It
    -1.18
     Vainqueur
    -1.16
    seys
    -1.15
    0
    -1.13
    When
    -1.13
    khid
    -1.10
    POSITIVE LOGITS
    cún
    1.34
     planeta
    1.29
    
    1.15
     capilar
    1.14
     comportement
    1.13
     インナー
    1.13
     online
    1.13
    vernight
    1.12
     работой
    1.11
     its
    1.10
    Activations Density 0.104%

    No Known Activations