© 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. 22-GEMMASCOPE-RES-131K
    7. 64885
    Prev
    Next
    INDEX
    Explanations

    contrast and exceptions

    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_22/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
    صیلات
    -0.85
    噙
    -0.79
     если
    -0.76
     クロ
    -0.75
     اگر
    -0.73
    >>>>>>
    -0.73
    后来
    -0.72
     fournies
    -0.71
    𝕥
    -0.71
     gero
    -0.71
    POSITIVE LOGITS
     currently
    2.44
     presently
    1.91
     сейчас
    1.86
     current
    1.83
     today
    1.75
    Currently
    1.64
     already
    1.58
    currently
    1.55
     пока
    1.55
    当前
    1.55
    Activations Density 0.058%

    No Known Activations