© 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. 10-GEMMASCOPE-RES-131K
    4. 20386
    Prev
    Next
    INDEX
    Explanations

    words following parentheses

    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
    </td>
    -1.88
    ↵↵↵
    -1.57
    ↵↵
    -1.48
     amable
    -1.43
    ↵↵↵↵↵
    -1.39
    简称
    -1.30
    ↵↵↵↵↵↵↵↵
    -1.27
    ↵↵↵↵
    -1.25
     și
    -1.23
    なんか
    -1.23
    POSITIVE LOGITS
     ofrece
    1.47
     jälkeen
    1.46
     diferentes
    1.45
     größe
    1.44
    __":
    
    1.38
    tisp
    1.38
    olymers
    1.38
    mans
    1.37
    もの
    1.36
    饪
    1.36
    Activations Density 0.049%

    No Known Activations