© 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. 10-GEMMASCOPE-RES-131K
    7. 12445
    Prev
    Next
    INDEX
    Explanations

    directed by, developed for

    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
    เรา
    -1.39
    FunctionFlags
    -1.35
     as
    -1.35
              
    -1.34
    我们
    -1.19
     môže
    -1.19
     we
    -1.17
     všetky
    -1.16
                  
    -1.16
    на
    -1.15
    POSITIVE LOGITS
    zzet
    1.38
    何故
    1.34
    昔の
    1.30
    Inserting
    1.30
    ervé
    1.29
     рассказывает
    1.28
     建物
    1.27
     about
    1.25
    .--
    1.23
     something
    1.22
    Activations Density 0.310%

    No Known Activations