© 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. 46
    Prev
    Next
    INDEX
    Explanations

    most followed by superlatives

    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
    ჻
    -1.49
    leiding
    -1.43
     掃除
    -1.34
     LOV
    -1.34
     MAIN
    -1.33
    danh
    -1.32
     MAKING
    -1.31
    bno
    -1.31
     ANY
    -1.30
    ឪ
    -1.30
    POSITIVE LOGITS
     also
    1.66
     definitely
    1.43
     quite
    1.35
     також
    1.34
     will
    1.33
     went
    1.29
    ：……
    1.27
     several
    1.21
     took
    1.20
    实践
    1.20
    Activations Density 0.022%

    No Known Activations