© 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. 128524
    Prev
    Next
    INDEX
    Explanations

    recipient/cc/email addressing

    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
     trà
    -1.12
    などに
    -1.09
     chcete
    -1.05
     trzech
    -1.04
    ༵
    -1.03
     máte
    -0.99
     kwiet
    -0.97
    ですよね
    -0.97
     komfort
    -0.97
    
    -0.96
    POSITIVE LOGITS
    zyst
    1.06
     =
    0.97
    ཇ
    0.96
     substandard
    0.95
     manta
    0.94
    ――――
    0.94
    árl
    0.93
    墨西哥
    0.93
     iguana
    0.91
     philanthrop
    0.89
    Activations Density 0.004%

    No Known Activations