© 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. 77996
    Prev
    Next
    INDEX
    Explanations

    code keywords or identifiers

    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
     LUT
    -0.94
    imum
    -0.89
     greate
    -0.89
     sitesinde
    -0.88
     sone
    -0.88
    -</
    -0.88
     ETL
    -0.88
     участ
    -0.88
    多く
    -0.88
     **/
    -0.87
    POSITIVE LOGITS
     with
    2.00
     without
    1.39
     revised
    1.34
     any
    1.31
     без
    1.30
    普通的
    1.28
     single
    1.19
    Belum
    1.15
     non
    1.13
     какво
    1.12
    Activations Density 0.059%

    No Known Activations