© 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. 78638
    Prev
    Next
    INDEX
    Explanations

    showing performance or action

    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
     karier
    -0.86
    badan
    -0.85
    tedly
    -0.83
     telefonu
    -0.82
    Album
    -0.78
     éxito
    -0.74
     quede
    -0.74
     Пла
    -0.74
    kron
    -0.73
     salonu
    -0.73
    POSITIVE LOGITS
     showing
    1.20
     showed
    1.12
     показать
    1.00
     deliver
    0.91
     demonstrating
    0.89
     performing
    0.88
     corrected
    0.88
     level
    0.84
     demonstrate
    0.82
     show
    0.82
    Activations Density 0.010%

    No Known Activations