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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49936
    Prev
    Next
    INDEX
    Explanations

    installs or provides services

    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_34/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
     dokonce
    -1.20
    Even
    -1.19
     even
    -1.12
     what
    -1.09
     because
    -1.03
    ̐
    -1.02
    đèn
    -1.02
    なんと
    -1.02
     their
    -1.01
     навіть
    -1.00
    POSITIVE LOGITS
     assigned
    1.12
    😦
    1.08
    perry
    1.06
    ictwa
    1.03
    हित
    0.97
     Company
    0.97
     سایر
    0.94
      
    0.94
     vader
    0.94
     ananas
    0.93
    Activations Density 0.043%

    No Known Activations