© 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. 41318
    Prev
    Next
    INDEX
    Explanations

    AND ,"},"token":" to","explanation":"AND,"}

    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
     trám
    -1.13
     květ
    -1.10
     какой
    -1.10
    тивного
    -1.09
     rám
    -1.08
     visualización
    -1.07
    Hogyan
    -1.06
     différente
    -1.05
     verschillende
    -1.04
     desej
    -1.04
    POSITIVE LOGITS
     Herv
    1.19
    ;
    1.13
     so
    1.13
     setelah
    1.13
     💜
    1.12
    Карьера
    1.05
     ]}
    1.05
     Although
    1.05
     ricardo
    1.05
     November
    1.04
    Activations Density 0.531%

    No Known Activations