© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 130163
    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
     so
    -1.28
    <bos>
    -1.27
     this
    -1.26
     to
    -1.19
    oflavin
    -1.18
     as
    -1.14
     any
    -1.13
     having
    -1.13
     with
    -1.09
     only
    -1.09
    POSITIVE LOGITS
    変わらず
    1.14
     extermination
    1.13
    適当
    1.13
     asemenea
    1.12
          
    1.12
     intima
    1.10
     również
    1.09
    ten
    1.09
    きち
    1.09
       
    1.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.