© 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. 34-GEMMASCOPE-RES-131K
    7. 29982
    Prev
    Next
    INDEX
    Explanations

    Kiss slowly, then I, so I

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     burgeoning
    -1.38
     first
    -1.32
     nestled
    -1.30
     undeniably
    -1.28
     troubling
    -1.25
     aiming
    -1.24
     battling
    -1.21
     using
    -1.21
     putting
    -1.20
     which
    -1.19
    POSITIVE LOGITS
    commonly
    1.34
    formerly
    1.32
    thodoxy
    1.27
    particularly
    1.26
     EVEN
    1.22
    -#
    1.22
     unn
    1.20
    sometimes
    1.19
    often
    1.19
     WIL
    1.19
    Activations Density 0.035%

    No Known Activations