© 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. 22-GEMMASCOPE-RES-131K
    7. 12533
    Prev
    Next
    INDEX
    Explanations

    news reporting and coverage

    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_22/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
    ׇ
    -1.48
    níků
    -1.32
     النبات
    -1.21
     گیاه
    -1.19
     biedt
    -1.16
    饌
    -1.13
    midler
    -1.13
     Âge
    -1.13
     skóry
    -1.07
    świad
    -1.06
    POSITIVE LOGITS
     news
    2.06
     coverage
    1.71
     journalism
    1.55
     бампер
    1.50
    ᾿
    1.45
    וּ
    1.41
     reporting
    1.39
     News
    1.31
     information
    1.29
     habari
    1.28
    Activations Density 0.068%

    No Known Activations