© 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. 112837
    Prev
    Next
    INDEX
    Explanations

    citations in brackets like [@B1]

    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
    犇
    -2.67
    出了一
    -2.45
    忖
    -2.42
    ↵
    -2.38
    箇
    -2.34
     After
    -2.27
    箔
    -2.25
    取締
    -2.23
    七月
    -2.20
    ↑↑↑</
    -2.20
    POSITIVE LOGITS
    たまに
    2.75
    筇
    2.59
    
    2.56
    本当は
    2.44
     alcune
    2.44
    がっ
    2.44
    割と
    2.42
    不會
    2.41
    羕
    2.41
     the
    2.39
    Activations Density 0.002%

    No Known Activations