© 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. 72993
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     that
    -1.15
     polícia
    -1.03
    gantian
    -0.99
    Ϟ
    -0.97
     nantinya
    -0.97
     ataupun
    -0.97
     sudadera
    -0.96
     reforzar
    -0.94
    déric
    -0.92
     diharapkan
    -0.92
    POSITIVE LOGITS
    th
    1.05
              
    1.05
    Zitat
    1.00
     lejos
    0.92
    比如说
    0.91
     belki
    0.91
     málo
    0.91
         
    0.91
    ont
    0.90
             
    0.90
    Activations Density 0.015%

    No Known Activations