© 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. 115921
    Prev
    Next
    INDEX
    Explanations

    last item in sequence

    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
     secondly
    -1.08
     Secondly
    -0.94
    nolia
    -0.94
    🥈
    -0.93
    Semitic
    -0.91
    kipun
    -0.87
    🕉
    -0.86
     potvr
    -0.82
     discípulos
    -0.82
     söyledi
    -0.81
    POSITIVE LOGITS
    Lastly
    1.41
    Finally
    1.34
     last
    1.33
     schließlich
    1.29
     Lastly
    1.24
     final
    1.23
     cuối
    1.19
    Last
    1.19
     terakhir
    1.16
    最后一
    1.13
    Activations Density 0.058%

    No Known Activations