© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130130
    Prev
    Next
    INDEX
    Explanations

    best way to do something

    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
     you
    -2.16
     was
    -1.52
    if
    -1.47
    minated
    -1.42
    geſ
    -1.37
     إذا
    -1.37
    䊐
    -1.35
     amely
    -1.33
    
    -1.33
     jika
    -1.32
    POSITIVE LOGITS
     sierpnia
    1.58
     września
    1.54
     kwietnia
    1.46
     stycznia
    1.45
     资料
    1.40
     subaru
    1.40
     nissan
    1.37
     czerwca
    1.33
    異なります
    1.30
     not
    1.29
    Activations Density 0.106%

    No Known Activations