© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76943
    Prev
    Next
    INDEX
    Explanations

    unsubscribe links

    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
    然的
    -0.86
     dia
    -0.82
    jną
    -0.81
    IntArray
    -0.79
     immobili
    -0.79
     ͜ʖ
    -0.77
     immobilized
    -0.76
     Paperback
    -0.75
     交換
    -0.74
    Bak
    -0.73
    POSITIVE LOGITS
     unsubscribe
    1.15
     recipients
    1.05
    Unsubscribe
    1.02
     recipient
    0.96
    unsubscribe
    0.93
     forward
    0.92
     forwarded
    0.91
     退
    0.84
    Preferences
    0.82
     newsletter
    0.82
    Activations Density 0.052%

    No Known Activations