© 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. 112580
    Prev
    Next
    INDEX
    Explanations

    gambling and betting options

    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
     had
    -1.48
     ผู้หญิง
    -1.45
     went
    -1.45
     problems
    -1.43
     types
    -1.41
     without
    -1.41
     and
    -1.41
    🦣
    -1.40
     rodilla
    -1.40
     fábricas
    -1.39
    POSITIVE LOGITS
     procéder
    1.88
     you
    1.88
    进入了
    1.84
    踌
    1.79
     menetap
    1.79
    饷
    1.77
    酝
    1.74
     your
    1.74
    久し
    1.73
    
    1.67
    Activations Density 0.111%

    No Known Activations