© 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. 10005
    Prev
    Next
    INDEX
    Explanations

    first or over

    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
     “
    -1.48
     P
    -1.35
     acompañada
    -1.34
     C
    -1.25
     featuring
    -1.25
    MICA
    -1.24
    对其
    -1.21
     dicha
    -1.20
    特殊的
    -1.20
    杙
    -1.20
    POSITIVE LOGITS
     he
    1.50
     it
    1.50
     transparencia
    1.45
    苼
    1.39
     geef
    1.38
     soldadura
    1.37
     productividad
    1.36
     espesor
    1.35
    7
    1.35
    來到
    1.34
    Activations Density 0.361%

    No Known Activations