© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 28365
    Prev
    Next
    INDEX
    Explanations

    questions about extent or degree

    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
    ทุก
    -0.96
     matka
    -0.94
     vitamine
    -0.93
    !」
    -0.92
     parfum
    -0.91
    fitted
    -0.91
    ging
    -0.90
     compagn
    -0.90
     เว
    -0.90
     faits
    -0.88
    POSITIVE LOGITS
     various
    1.80
     these
    1.79
     each
    1.75
     this
    1.53
     extent
    1.41
     or
    1.37
     poszczegól
    1.29
     зависит
    1.27
     Various
    1.27
     different
    1.26
    Activations Density 0.101%

    No Known Activations