© 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. 10-GEMMASCOPE-RES-131K
    7. 100698
    Prev
    Next
    INDEX
    Explanations

    buy or purchase

    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_10/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
    est
    -1.51
    /
    -1.37
    (?)
    -1.34
    -1.30
    尤其是
    -1.30
     +
    -1.30
     }
    -1.24
     \
    -1.23
     ل
    -1.23
     /
    -1.16
    POSITIVE LOGITS
     from
    1.54
     where
    1.48
     boty
    1.36
     nuovi
    1.33
    购买
    1.33
     nuevos
    1.32
     赵
    1.30
    鸸
    1.30
    purchased
    1.30
     Buying
    1.27
    Activations Density 0.096%
    No Known Activations