© 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. 49
    Prev
    Next
    INDEX
    Explanations

    classification metrics

    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
    During
    -1.19
     how
    -1.17
     what
    -1.10
    只是一
    -0.93
     developments
    -0.93
    hinder
    -0.92
     зданий
    -0.90
    what
    -0.90
    »,
    -0.90
     changes
    -0.88
    POSITIVE LOGITS
     какъ
    1.23
     възможно
    1.13
     trebui
    1.07
    cún
    1.07
    ріш
    1.06
     rady
    1.05
     trabajo
    1.05
    ättning
    1.05
    ниците
    1.05
     защото
    1.05
    Activations Density 0.003%

    No Known Activations