© 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. 10-GEMMASCOPE-RES-131K
    7. 42798
    Prev
    Next
    INDEX
    Explanations

    programming and technical terms

    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_10/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
    amazing
    -1.44
    覿
    -1.43
     valuta
    -1.39
    
    -1.38
    forty
    -1.34
     horrifying
    -1.34
    榫
    -1.33
    ithin
    -1.30
    decla
    -1.30
    eleven
    -1.27
    POSITIVE LOGITS
     as
    1.77
     for
    1.66
     only
    1.65
     not
    1.64
     like
    1.47
     increased
    1.45
     September
    1.45
     with
    1.42
     on
    1.38
     essentially
    1.38
    Activations Density 0.189%

    No Known Activations