© 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. 75380
    Prev
    Next
    INDEX
    Explanations

    unnecessary rulings

    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
    ↵↵
    -1.84
     '
    -1.77
     It
    -1.60
     sottile
    -1.44
     Why
    -1.34
     erfolgreichen
    -1.34
     його
    -1.34
     защото
    -1.34
     brachte
    -1.34
     verbindet
    -1.34
    POSITIVE LOGITS
     saat
    1.82
    itize
    1.74
    matory
    1.65
    ibility
    1.65
    saat
    1.61
    leicht
    1.57
    ᥀
    1.57
    itisation
    1.57
     mula
    1.52
    箧
    1.52
    Activations Density 0.005%

    No Known Activations