© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 8679
    Prev
    Next
    INDEX
    Explanations

    CSS statement terminator

    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
    𒊹
    -2.38
    -
    -2.38
     début
    -2.25
    
    -2.14
    她就
    -2.14
    providedIn
    -2.05
    Should
    -2.05
    
    -2.03
    >
    -2.02
    both
    -1.98
    POSITIVE LOGITS
    ↵↵
    2.61
     or
    2.03
     těch
    1.95
     they
    1.95
     碗
    1.89
    )|^{
    1.89
    e
    1.87
     that
    1.85
     ktoré
    1.80
     ljudi
    1.78
    Activations Density 0.013%

    No Known Activations