© 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. 123939
    Prev
    Next
    INDEX
    Explanations

    abbreviations for parts of words

    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
     indicates
    -2.70
     specified
    -2.67
     sodass
    -2.55
    沇
    -2.48
     provides
    -2.48
     includes
    -2.47
     confirms
    -2.47
     gives
    -2.47
     tells
    -2.45
    酲
    -2.45
    POSITIVE LOGITS
     terrific
    2.67
     unbelievably
    2.66
     AMAZING
    2.64
    having
    2.63
     decidedly
    2.58
     amazingly
    2.53
     soooo
    2.52
     '
    2.50
    在我
    2.48
     quintessential
    2.36
    Activations Density 0.034%

    No Known Activations