© 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. 85218
    Prev
    Next
    INDEX
    Explanations

    fully understand or appreciate

    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
    遢
    -1.84
     mindig
    -1.68
     inkább
    -1.46
     zuständig
    -1.46
    сам
    -1.45
     uſed
    -1.36
    puerto
    -1.30
    熥
    -1.30
    ющие
    -1.30
    
    -1.29
    POSITIVE LOGITS
    s
    1.59
    8
    1.58
     firft
    1.56
    nological
    1.53
    gered
    1.52
    tiest
    1.52
    Y
    1.51
    neling
    1.49
     даже
    1.48
     onsdag
    1.48
    Activations Density 0.027%

    No Known Activations