© 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. 22-GEMMASCOPE-RES-131K
    7. 95728
    Prev
    Next
    INDEX
    Explanations

    patent documents

    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_22/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
     with
    -2.36
     in
    -2.02
     on
    -1.87
     at
    -1.55
     from
    -1.32
     all
    -1.31
     that
    -1.30
    pography
    -1.30
     to
    -1.27
     may
    -1.27
    POSITIVE LOGITS
    皷
    1.54
     alcune
    1.54
     diversos
    1.48
     DURING
    1.45
     offensichtlich
    1.36
    おそ
    1.34
     acclaimed
    1.31
     pesso
    1.30
     ۔
    1.29
     különböző
    1.29
    Activations Density 0.012%

    No Known Activations