© 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. 26759
    Prev
    Next
    INDEX
    Explanations

    command line arguments or code

    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
    ָּ
    -0.89
     niem
    -0.87
     DELLE
    -0.87
    jakarta
    -0.85
     vetro
    -0.84
     живота
    -0.84
    शु
    -0.82
     vidro
    -0.81
    িয়া
    -0.81
    ÍO
    -0.79
    POSITIVE LOGITS
    eiro
    0.91
    Procedimento
    0.91
    ні
    0.83
     berea
    0.80
    לְ
    0.79
    miert
    0.79
    stationary
    0.78
    嵌入
    0.78
     Territories
    0.78
    Cuáles
    0.78
    Activations Density 0.024%

    No Known Activations