© 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. 22-GEMMASCOPE-RES-131K
    7. 36635
    Prev
    Next
    INDEX
    Explanations

    by or because of reason

    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_22/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
     five
    -1.07
    胯
    -0.98
     four
    -0.98
     seven
    -0.97
     parfüm
    -0.96
     Тро
    -0.94
     Шев
    -0.94
    ꪔ
    -0.93
     ועל
    -0.92
     but
    -0.91
    POSITIVE LOGITS
    now
    1.23
    Теперь
    1.12
     bardziej
    1.03
    Instead
    0.96
    being
    0.94
     instead
    0.93
    noons
    0.93
     able
    0.91
    少了
    0.91
     fewer
    0.90
    Activations Density 0.043%

    No Known Activations