© 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. 65407
    Prev
    Next
    INDEX
    Explanations

    words ending in er/ers

    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
     \
    -2.84
    5
    -2.81
     '
    -2.72
    0
    -2.41
     für
    -2.34
    3
    -2.28
    ",
    -2.27
    \\
    -2.27
    ，
    -2.23
     -
    -2.22
    POSITIVE LOGITS
    !’
    3.33
    屺
    3.16
    塒
    2.95
    ’:
    2.94
    찡
    2.73
    ᨘ
    2.72
    塤
    2.67
    籏
    2.66
     feroit
    2.59
    =’
    2.59
    Activations Density 0.011%

    No Known Activations