© 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. 9183
    Prev
    Next
    INDEX
    Explanations

    how what why questions

    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
     یکی
    -1.73
    bsen
    -1.43
    喜欢
    -1.38
    Можно
    -1.37
     frère
    -1.36
    イタリア
    -1.35
     doporu
    -1.33
     desnuda
    -1.30
    はい
    -1.28
    全球
    -1.28
    POSITIVE LOGITS
     about
    1.77
     both
    1.66
     our
    1.53
    0
    1.52
     Our
    1.47
    mappedBy
    1.41
     we
    1.41
     other
    1.39
    canActivate
    1.35
     others
    1.34
    Activations Density 0.099%

    No Known Activations