© 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. 117941
    Prev
    Next
    INDEX
    Explanations

    IT enterprise software

    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
     pelanggan
    -0.90
    skoda
    -0.88
     kereta
    -0.85
    YourGuide
    -0.84
     真
    -0.83
     pintu
    -0.82
    Pz
    -0.81
     Хе
    -0.80
     pekan
    -0.80
    ПП
    -0.80
    POSITIVE LOGITS
    IT
    0.91
     CIO
    0.88
     Fut
    0.85
    Enterprise
    0.85
    MEAN
    0.84
     IT
    0.81
    inal
    0.80
    ⊑
    0.79
    enterprise
    0.78
     DUST
    0.77
    Activations Density 0.019%

    No Known Activations