© 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. 64466
    Prev
    Next
    INDEX
    Explanations

    we or our

    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
     could
    -1.45
     did
    -1.23
     which
    -1.22
     went
    -1.19
     actually
    -1.17
     began
    -1.17
     during
    -1.16
     drastically
    -1.16
     one
    -1.16
     completely
    -1.15
    POSITIVE LOGITS
     nasz
    1.52
    worldwide
    1.30
    }:{
    1.27
     écl
    1.22
    commonly
    1.22
     cordes
    1.21
     نحن
    1.20
    myself
    1.19
    (“
    1.18
    against
    1.17
    Activations Density 0.046%

    No Known Activations