© 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. 9975
    Prev
    Next
    INDEX
    Explanations

    automobile and motor manufacturers

    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
     or
    -1.44
    ΐ
    -1.30
     lil
    -1.20
    ؋
    -1.16
    !
    -1.16
     inflatable
    -1.15
     heridas
    -1.13
    λλ
    -1.13
     o
    -1.12
    自分が
    -1.11
    POSITIVE LOGITS
     cooperación
    1.62
     serão
    1.48
    Zubereitung
    1.37
    Elaboración
    1.34
     configuração
    1.34
    笵
    1.32
     estratégia
    1.31
     cópia
    1.30
    gehenden
    1.30
     how
    1.27
    Activations Density 0.051%

    No Known Activations