© 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. 83973
    Prev
    Next
    INDEX
    Explanations

    common phrases and collocations

    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
     obtaining
    -1.13
     compreender
    -1.07
    Cannot
    -1.05
     obtains
    -1.02
     comenz
    -1.02
    cannot
    -1.01
     نیز
    -1.00
     obtain
    -1.00
     sufficiently
    -0.99
    dapat
    -0.99
    POSITIVE LOGITS
     maybe
    1.05
     чтоб
    1.01
     żeby
    1.00
     gotten
    0.98
     ज्यादा
    0.96
     isn
    0.92
     grandkids
    0.92
     ३
    0.91
     kids
    0.91
    টা
    0.91
    Activations Density 0.041%

    No Known Activations