© 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. 9833
    Prev
    Next
    INDEX
    Explanations

    expressing desire or necessity

    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
     podem
    -0.91
     opportunity
    -0.88
     additional
    -0.87
    ﷽
    -0.87
    <bos>
    -0.86
    ify
    -0.85
    startGame
    -0.85
     may
    -0.85
     continues
    -0.84
     ایالات
    -0.84
    POSITIVE LOGITS
    Doing
    1.30
     Dabei
    1.20
     hacerlo
    1.19
     daarbij
    1.17
    doing
    1.09
     farlo
    1.09
     melakukannya
    1.07
    using
    1.01
     dabei
    0.97
     Doing
    0.93
    Activations Density 0.172%

    No Known Activations