© 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. 127940
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     this
    -1.45
     their
    -1.32
    呖
    -1.30
    〜。
    -1.18
     those
    -1.16
     any
    -1.09
     fhew
    -1.09
    𖡼
    -1.07
     sehr
    -1.07
     intense
    -1.06
    POSITIVE LOGITS
     probablement
    1.21
    actually
    1.20
    specifically
    1.13
     REALLY
    1.13
     INCREASE
    1.07
     ENH
    1.06
     jouent
    1.05
    could
    1.05
    possibly
    1.04
     présentent
    1.04
    Activations Density 0.000%

    No Known Activations