© 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. 99561
    Prev
    Next
    INDEX
    Explanations

    w followed by punctuation or symbol

    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
    w
    -3.30
    From
    -3.19
    ↵
    -3.14
    Not
    -3.13
    It
    -3.13
    Having
    -3.13
    With
    -3.08
    You
    -3.08
    There
    -3.05
    </strong>
    -2.95
    POSITIVE LOGITS
     '
    2.73
     was
    2.61
    岀
    2.56
    
    2.56
    🫅
    2.55
    ྂ
    2.52
     w
    2.47
    饧
    2.47
    
    2.45
     hrab
    2.36
    Activations Density 0.006%

    No Known Activations