© 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. 127768
    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
    Negative Logits
    を読んで
    -1.13
     its
    -1.13
    ſten
    -1.09
    Specifica
    -1.06
    を読
    -1.02
     alza
    -1.02
    Materiale
    -1.01
     Entdecke
    -0.98
     azule
    -0.97
     abuso
    -0.96
    POSITIVE LOGITS
    ’
    1.41
    ”
    1.23
    GH
    1.14
    ærer
    1.12
     eredmény
    1.10
    “
    1.03
    !
    1.02
    oes
    1.02
     emlé
    1.00
    ,
    0.98
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.