© 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. 82582
    Prev
    Next
    INDEX
    Explanations

    code comments and announcements

    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
     so
    -1.34
     first
    -1.29
     this
    -1.05
     remained
    -1.03
     and
    -1.03
     went
    -1.03
     since
    -1.02
     began
    -1.01
     while
    -0.99
     will
    -0.98
    POSITIVE LOGITS
    URAS
    1.17
     débuts
    1.16
    糅
    1.13
     brinquedos
    1.09
     jouets
    1.09
     NEEDED
    1.08
       
    1.08
     delectable
    1.07
     люб
    1.05
     ludicrous
    1.05
    Activations Density 0.000%

    No Known Activations