© 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. 127408
    Prev
    Next
    INDEX
    Explanations

    closing code punctuation

    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
    $
    -3.14
    },
    -3.08
    And
    -2.83
    On
    -2.67
    Like
    -2.66
    if
    -2.61
    “,
    -2.48
    ’
    -2.48
    Only
    -2.47
    e
    -2.45
    POSITIVE LOGITS
     conocidas
    2.53
     comienzan
    2.42
     dalších
    2.41
     queridos
    2.33
    ?"
    2.31
     funcionan
    2.30
     contienen
    2.27
    啬
    2.27
     vienen
    2.22
     serían
    2.22
    Activations Density 0.007%

    No Known Activations