© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 2903
    Prev
    Next
    INDEX
    Explanations

    Wikipedia contributions and edits

    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_34/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
    رارة
    -0.98
     cleverly
    -0.96
     only
    -0.95
     all
    -0.92
    Źródło
    -0.90
    选择
    -0.89
     sehr
    -0.89
     not
    -0.88
    ilität
    -0.88
    Zobacz
    -0.88
    POSITIVE LOGITS
     Wikipedia
    1.33
     additions
    1.30
     edit
    1.27
     edits
    1.22
    Wikipedia
    1.22
     braccia
    1.20
     contributions
    1.17
     wiki
    1.14
     encyclopedia
    1.12
     stubs
    1.12
    Activations Density 0.001%

    No Known Activations