© 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. 106298
    Prev
    Next
    INDEX
    Explanations

    numbers and codes

    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
     after
    -1.04
     during
    -0.98
     at
    -0.96
     AnyObject
    -0.90
    frontmatter
    -0.89
     with
    -0.87
     steadily
    -0.87
    After
    -0.86
    During
    -0.84
     pursue
    -0.84
    POSITIVE LOGITS
    Stations
    0.94
     vernis
    0.91
     siff
    0.90
     klip
    0.88
     DEPT
    0.83
     sachant
    0.83
     secr
    0.82
    ∖
    0.81
     kame
    0.81
    ishw
    0.81
    Activations Density 0.014%

    No Known Activations