© 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. 58887
    Prev
    Next
    INDEX
    Explanations

    `chr` followed by numbers in parentheses

    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
    Lastly
    -1.50
    Finally
    -1.46
     that
    -1.33
     Lastly
    -1.31
     Finally
    -1.19
     lastly
    -1.15
    最后一个
    -1.13
     would
    -1.08
    reszcie
    -1.02
    Enfin
    -1.02
    POSITIVE LOGITS
     keineswegs
    1.09
     giusta
    1.03
     浅
    1.01
     quintessential
    1.01
     alcune
    1.00
    riller
    0.97
    iners
    0.94
    gre
    0.93
     mediocre
    0.93
     weiterhin
    0.92
    Activations Density 0.096%

    No Known Activations