© 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. 68817
    Prev
    Next
    INDEX
    Explanations

    actions followed by context

    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
     to
    -1.43
     Finally
    -1.24
    finally
    -1.21
     utilisent
    -1.18
     which
    -1.18
     pios
    -1.17
     enfin
    -1.16
    ˆ
    -1.16
     finally
    -1.15
    RequestMethod
    -1.15
    POSITIVE LOGITS
     their
    1.32
     atacado
    1.32
     comprometido
    1.29
     wichtigen
    1.28
     atendido
    1.27
     provocado
    1.27
     silencioso
    1.26
     sucedido
    1.26
     encontraba
    1.23
     erforder
    1.21
    Activations Density 0.407%

    No Known Activations