© 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. 65174
    Prev
    Next
    INDEX
    Explanations

    words beginning with "Pon"

    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
    0
    -3.42
    to
    -2.95
    .
    -2.86
    3
    -2.66
    是真的
    -2.53
    ে
    -2.48
    ING
    -2.48
    或者
    -2.41
    this
    -2.38
    2
    -2.36
    POSITIVE LOGITS
     indescri
    2.53
     公主
    2.50
    URLException
    2.50
    嵓
    2.45
    transQ
    2.44
    釙
    2.38
     また
    2.33
    𝄆
    2.33
    agian
    2.30
    餿
    2.30
    Activations Density 0.005%

    No Known Activations