© 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. 113621
    Prev
    Next
    INDEX
    Explanations

    beyond merely

    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
    ↵↵
    -1.70
    </h3>
    -1.68
     This
    -1.59
    いずれ
    -1.52
     —
    -1.48
     Apparently
    -1.46
     επίσης
    -1.44
    \
    -1.44
     is
    -1.42
     difference
    -1.41
    POSITIVE LOGITS
     than
    1.94
     etek
    1.75
    蔟
    1.70
     イラストレーション
    1.66
    歃
    1.65
     レスト
    1.61
    顚
    1.61
    ୌ
    1.59
    ︕
    1.59
     pandemi
    1.56
    Activations Density 0.022%

    No Known Activations