© 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. 12926
    Prev
    Next
    INDEX
    Explanations

    some followed by a noun

    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
    栳
    -2.42
    烀
    -2.23
    毟
    -2.20
    
    -2.20
    ꯷
    -2.13
    但我
    -2.11
    狴
    -2.11
     absolut
    -2.11
     elaboración
    -2.08
    言うと
    -2.08
    POSITIVE LOGITS
     of
    3.23
     gave
    2.33
    </h3>
    2.28
     promotes
    2.27
     ostensibly
    2.23
    「
    2.19
    WHAT
    2.19
     categorized
    2.14
    全世界
    2.14
     saumon
    2.13
    Activations Density 0.086%

    No Known Activations