© 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. 75021
    Prev
    Next
    INDEX
    Explanations

    cob, tesco, usart, sok

    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
    琑
    -2.67
     
    -2.55
    hamilan
    -2.53
    崀
    -2.48
    ⩕
    -2.36
    是要
    -2.28
    THE
    -2.25
    鶿
    -2.22
    鸰
    -2.22
     нов
    -2.17
    POSITIVE LOGITS
    ),
    2.73
    .,
    2.45
     könnten
    2.34
    }$
    2.34
     the
    2.31
     Bereichen
    2.28
     dwindling
    2.28
     defunct
    2.28
     nuanced
    2.28
     bewilder
    2.27
    Activations Density 0.006%

    No Known Activations