© 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. 36073
    Prev
    Next
    INDEX
    Explanations

    hexadecimal numbers and intensifiers likeamazingly

    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
    Having
    -2.48
    Usually
    -2.47
    With
    -2.36
    Even
    -2.36
    Before
    -2.34
    Despite
    -2.33
    Shortly
    -2.31
    Often
    -2.30
    While
    -2.23
    Since
    -2.19
    POSITIVE LOGITS
     shimmering
    2.36
     unbelievably
    2.34
     amazingly
    2.33
     ridiculously
    2.33
     luscious
    2.30
     delightfully
    2.25
     marvelous
    2.25
     decidedly
    2.23
     dreary
    2.23
     REALLY
    2.17
    Activations Density 0.003%

    No Known Activations