© 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. 75216
    Prev
    Next
    INDEX
    Explanations

    opcodes and codes

    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
    ):
    -2.19
     навіть
    -2.08
    be
    -2.08
     concerted
    -1.97
    "?
    -1.97
     следующим
    -1.95
     have
    -1.94
    ?".
    -1.91
    ro
    -1.85
    --
    -1.85
    POSITIVE LOGITS
    嫆
    2.27
    เพื่อ
    2.22
    𓍊
    2.05
    かもしれません
    2.03
     nacimiento
    1.98
            
    1.97
     borboleta
    1.97
     tatuagem
    1.95
    𐐪
    1.92
    ឵
    1.91
    Activations Density 0.001%

    No Known Activations