© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 36237
    Prev
    Next
    INDEX
    Explanations

    items with specific functions

    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
    няли
    -1.00
     initComponents
    -0.98
    ğine
    -0.93
    EFAULT
    -0.93
    стых
    -0.91
    駅から
    -0.89
    辉
    -0.87
     Francus
    -0.85
    回目
    -0.83
    šej
    -0.82
    POSITIVE LOGITS
     useful
    2.00
     used
    1.88
    用途
    1.80
    useful
    1.57
     usefulness
    1.45
     kullanı
    1.40
     usos
    1.38
     Useful
    1.38
    Used
    1.35
     versatility
    1.35
    Activations Density 0.214%

    No Known Activations