© 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. 84924
    Prev
    Next
    INDEX
    Explanations

    delivered or returned

    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
    coat
    -0.83
     quickly
    -0.81
     ellen
    -0.79
    tains
    -0.79
    }$​
    -0.75
    sentry
    -0.74
     for
    -0.71
     summon
    -0.71
    oge
    -0.70
    няются
    -0.70
    POSITIVE LOGITS
     delivered
    1.16
     postage
    1.13
     receipt
    1.06
    RECEIVED
    1.05
     mailed
    1.05
    received
    1.03
     FAX
    1.02
    Late
    1.02
     RECEIVED
    1.02
     received
    1.00
    Activations Density 0.017%

    No Known Activations