© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128582
    Prev
    Next
    INDEX
    Explanations

    things described as interesting

    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
    是
    -3.22
    ه
    -2.95
    
    -2.72
    不
    -2.63
    裥
    -2.61
     lauded
    -2.53
     TIME
    -2.52
     trovo
    -2.45
    𖣔
    -2.44
    有可能
    -2.41
    POSITIVE LOGITS
    鋮
    3.05
    晅
    2.92
    .
    2.92
     thoughtful
    2.91
     intensely
    2.81
     That
    2.81
    ness
    2.66
     Surprisingly
    2.66
    下一篇
    2.64
    翾
    2.64
    Activations Density 0.008%

    No Known Activations