© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25007
    Prev
    Next
    INDEX
    Explanations

    imagine or think of

    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
    Negative Logits
    Mű
    -1.16
     castello
    -1.13
    struzione
    -1.10
     Schauspielerin
    -1.04
     giacca
    -1.04
     santuario
    -1.02
     quartiere
    -1.02
    存于
    -1.02
     اندروید
    -1.01
     ferie
    -1.00
    POSITIVE LOGITS
     your
    2.08
     like
    1.76
     you
    1.55
     imagine
    1.35
    Imagine
    1.34
     if
    1.31
     Imagine
    1.28
    Think
    1.23
     as
    1.23
     yourself
    1.22
    Activations Density 0.011%

    No Known Activations