© 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. 131054
    Prev
    Next
    INDEX
    Explanations

    derogatory language and humiliation

    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
     his
    -1.98
     About
    -1.84
     Are
    -1.75
     decides
    -1.72
     At
    -1.71
    p
    -1.69
     resists
    -1.69
     Our
    -1.64
     Who
    -1.63
     examines
    -1.63
    POSITIVE LOGITS
    埽
    1.98
     and
    1.78
     สอง
    1.68
     lc
    1.64
     altında
    1.64
    仉
    1.63
    !');
    1.63
    一下
    1.60
     blauwe
    1.60
    檍
    1.59
    Activations Density 0.008%

    No Known Activations