© 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. 92702
    Prev
    Next
    INDEX
    Explanations

    upper bound

    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
     bicicletas
    -0.87
     Мол
    -0.81
    வும்
    -0.79
     menahan
    -0.79
     наро
    -0.78
    聾
    -0.77
    érer
    -0.77
    DataService
    -0.76
     Saturday
    -0.76
     Шо
    -0.75
    POSITIVE LOGITS
     gully
    0.94
     hiel
    0.91
     stiefel
    0.89
     Tomáš
    0.87
    жешь
    0.83
     tages
    0.82
     GOtt
    0.82
     resell
    0.81
    cidae
    0.81
     alho
    0.79
    Activations Density 0.001%

    No Known Activations