© 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. 49467
    Prev
    Next
    INDEX
    Explanations

    arrival and packaging condition

    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
     you
    -0.94
    ૪
    -0.89
    iamo
    -0.84
     our
    -0.83
     unseres
    -0.82
    você
    -0.82
    lization
    -0.81
     once
    -0.80
    甜
    -0.80
     your
    -0.80
    POSITIVE LOGITS
     packaging
    1.73
     Packaging
    1.43
    packaging
    1.36
     packaged
    1.36
     undamaged
    1.35
    Packaging
    1.33
    packaged
    1.30
    Packaged
    1.26
    包裝
    1.13
     FedEx
    1.11
    Activations Density 0.014%

    No Known Activations