© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72281
    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
     if
    -1.49
     as
    -1.38
     tailored
    -1.27
     minas
    -1.22
     first
    -1.18
     tabaco
    -1.16
     achieve
    -1.16
     comerci
    -1.15
     from
    -1.14
     by
    -1.13
    POSITIVE LOGITS
     myriad
    1.24
     diversos
    1.22
     exceptionally
    1.20
     horrid
    1.17
     пять
    1.16
     languid
    1.14
     potrebbe
    1.13
     tumultuous
    1.13
     amazingly
    1.12
     momentous
    1.12
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.