© 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. 65922
    Prev
    Next
    INDEX
    Explanations

    currently active or open

    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
    țul
    -0.91
    での
    -0.90
     johnson
    -0.90
    作為
    -0.87
    🏨
    -0.83
    ден
    -0.83
     durante
    -0.81
     ciągu
    -0.79
     niem
    -0.78
    作为
    -0.77
    POSITIVE LOGITS
     currently
    2.59
    currently
    1.98
     current
    1.98
    Currently
    1.97
     현재
    1.70
     attualmente
    1.70
     presently
    1.63
    当前
    1.60
     đang
    1.57
    Actualmente
    1.52
    Activations Density 0.144%

    No Known Activations