© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66342
    Prev
    Next
    INDEX
    Explanations

    connecting clauses with and

    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
     mondiale
    -1.78
     adalah
    -1.76
    圌
    -1.65
    嫫
    -1.64
    齪
    -1.63
     constater
    -1.62
    
    -1.60
     スケッチ
    -1.60
     papeles
    -1.58
     linge
    -1.56
    POSITIVE LOGITS
     you
    2.36
     they
    2.20
    ↵
    2.09
    :
    2.08
     /
    2.03
     //
    2.02
     this
    1.92
     \
    1.84
     When
    1.84
    1.82
    Activations Density 0.055%

    No Known Activations