© 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. 2658
    Prev
    Next
    INDEX
    Explanations

    delivered or not delivered

    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
     Dadurch
    -0.98
     wodurch
    -0.95
    combs
    -0.90
     cucharadita
    -0.85
    Lösung
    -0.85
    hren
    -0.82
    bye
    -0.81
    μός
    -0.81
    ÓN
    -0.80
    ラル
    -0.80
    POSITIVE LOGITS
     deliver
    4.38
     delivered
    3.95
     delivering
    3.78
     delivers
    3.77
    deliver
    3.48
     Deliver
    3.42
    Deliver
    3.36
     delivery
    3.17
     DELIVER
    3.08
    delivered
    2.95
    Activations Density 0.037%

    No Known Activations