© 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. 103993
    Prev
    Next
    INDEX
    Explanations

    enhancement of

    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
    栳
    -2.31
    /
    -2.30
    的力量
    -2.25
    睒
    -2.19
    of
    -2.16
     veröffentlich
    -2.06
    )
    -2.05
     alterations
    -2.02
    鴒
    -2.00
    
    -1.98
    POSITIVE LOGITS
     –
    2.97
    tains
    2.48
    ments
    2.36
     sont
    2.33
    cayaan
    2.31
    ‪.‬‬
    2.28
    惕
    2.27
     disminuir
    2.25
    呖
    2.22
    kwür
    2.20
    Activations Density 0.013%

    No Known Activations