© 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. 128021
    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
     ministros
    -1.28
    pantal
    -1.24
     gonna
    -1.22
    assero
    -1.16
     capuz
    -1.13
     wolle
    -1.13
    diano
    -1.13
    gilet
    -1.11
    Kemudian
    -1.10
     estableció
    -1.10
    POSITIVE LOGITS
     or
    1.21
    দ
    1.05
     PLEAS
    1.05
    Gor
    1.05
     BORROW
    1.02
     marx
    1.00
     COUNTRIES
    0.99
    Swal
    0.99
     POUR
    0.99
     lojas
    0.98
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.