© 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. 253
    Prev
    Next
    INDEX
    Explanations

    uncertainty and possibility

    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
     then
    -0.98
    ELF
    -0.92
     avenida
    -0.90
    kelijkheid
    -0.89
    После
    -0.89
     permitan
    -0.88
    вої
    -0.85
     juc
    -0.84
    OTHER
    -0.84
    záll
    -0.84
    POSITIVE LOGITS
     each
    1.81
    随时
    1.46
     every
    1.36
    隨時
    1.23
     another
    1.13
     chaque
    1.11
     constantly
    1.10
     Each
    1.10
     каждом
    1.08
     unpredic
    1.06
    Activations Density 0.023%

    No Known Activations