© 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. 107169
    Prev
    Next
    INDEX
    Explanations

    calculating differences

    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
    Geographie
    -0.91
    τρ
    -0.91
     glo
    -0.90
     বা
    -0.85
    Scho
    -0.82
    veira
    -0.81
    ituksen
    -0.80
     银
    -0.80
    Composition
    -0.79
     voiture
    -0.79
    POSITIVE LOGITS
     difference
    1.61
     differences
    1.29
     diferença
    1.21
    Difference
    1.20
    Differences
    1.16
     Difference
    1.16
     Differences
    1.12
     разница
    1.09
    difference
    1.09
     -(
    1.00
    Activations Density 0.020%

    No Known Activations