© 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. 118567
    Prev
    Next
    INDEX
    Explanations

    legal jurisdiction headers

    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
     making
    -1.57
     before
    -1.56
     so
    -1.55
     people
    -1.52
     JUST
    -1.52
     after
    -1.50
     taking
    -1.47
     Despite
    -1.43
     all
    -1.41
     reduce
    -1.41
    POSITIVE LOGITS
     myriad
    1.61
     quintessential
    1.59
     ludicrous
    1.59
    !!!!!!!
    1.55
     !!!!
    1.54
     pivotal
    1.53
     cuatro
    1.52
     quirky
    1.49
     unbelievably
    1.49
     horrid
    1.48
    Activations Density 0.002%

    No Known Activations