© 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. 38445
    Prev
    Next
    INDEX
    Explanations

    contents followed by section titles

    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
     Pino
    -0.99
    ⸝
    -0.96
    Those
    -0.96
    Several
    -0.91
    ：@
    -0.90
     many
    -0.89
     those
    -0.88
     dozens
    -0.87
     Those
    -0.87
     Kung
    -0.86
    POSITIVE LOGITS
     why
    1.44
     Why
    1.08
     about
    0.97
     사용
    0.90
     Who
    0.90
    なぜ
    0.90
    List
    0.89
    ۱
    0.88
     agradec
    0.86
     äußer
    0.85
    Activations Density 0.079%

    No Known Activations