© 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. 119850
    Prev
    Next
    INDEX
    Explanations

    `.hide-title:hover`

    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
     a
    -1.52
     that
    -1.48
    ENARIO
    -1.37
     the
    -1.25
     luxo
    -1.22
    mott
    -1.21
    haviours
    -1.19
     Página
    -1.18
     applica
    -1.16
    曁
    -1.16
    POSITIVE LOGITS
     muerta
    1.30
    1
    1.26
    滄
    1.25
    How
    1.23
     моей
    1.19
     kerül
    1.17
    All
    1.16
    We
    1.13
     całość
    1.13
    Все
    1.13
    Activations Density 0.026%

    No Known Activations