© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 87047
    Prev
    Next
    INDEX
    Explanations

    URL redirection and rewrites

    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
     imbalance
    -0.82
     bypassed
    -0.78
     ônibus
    -0.77
    adillas
    -0.77
    vila
    -0.75
     ramos
    -0.74
     varanda
    -0.73
    Gare
    -0.72
    首次
    -0.72
    sack
    -0.72
    POSITIVE LOGITS
     redirect
    2.16
    redirect
    1.84
     redirects
    1.77
     Redirect
    1.68
    Redirect
    1.57
    Redire
    1.42
     redirection
    1.41
    REDIRECT
    1.35
     forwarding
    1.27
    redirectTo
    1.21
    Activations Density 0.087%

    No Known Activations