© 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. 34-GEMMASCOPE-RES-131K
    7. 30769
    Prev
    Next
    INDEX
    Explanations

    try blocks

    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_34/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
     incluso
    -0.91
     even
    -0.91
     lägga
    -0.89
     даже
    -0.89
     bygga
    -0.83
     säga
    -0.82
     regering
    -0.82
    久的
    -0.82
     nuevamente
    -0.80
     Ortsteil
    -0.79
    POSITIVE LOGITS
    try
    7.13
     try
    6.69
     Try
    4.88
    Try
    4.78
     tries
    4.72
     TRY
    4.56
     trying
    4.56
    TRY
    4.50
     tried
    4.22
     versuchen
    3.94
    Activations Density 0.049%

    No Known Activations