© 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. 48573
    Prev
    Next
    INDEX
    Explanations

    programming syntax and identifiers

    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
     captar
    -1.09
     such
    -0.92
     condena
    -0.87
     casó
    -0.86
     desorden
    -0.85
     mempel
    -0.84
    råd
    -0.84
    chm
    -0.84
     szeret
    -0.83
    hanging
    -0.81
    POSITIVE LOGITS
     patente
    0.94
      
    0.93
     ajustable
    0.90
     convient
    0.87
     refe
    0.87
    ᧐
    0.86
     .
    0.84
     tinto
    0.84
     iman
    0.84
    すでに
    0.83
    Activations Density 0.029%

    No Known Activations