© 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. 22-GEMMASCOPE-RES-131K
    7. 98479
    Prev
    Next
    INDEX
    Explanations

    past tense verbs and quantities

    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
     лука
    -1.46
     бампер
    -1.37
     меда
    -1.23
     első
    -1.16
    ülle
    -1.09
    Karakter
    -1.08
    ּוֹ
    -1.08
     衣
    -1.08
    giphy
    -1.07
    quarelle
    -1.07
    POSITIVE LOGITS
     was
    1.50
    –)
    1.45
     had
    1.33
     иллюстрация
    1.30
     wasn
    1.28
    吅
    1.28
     kinds
    1.27
     things
    1.26
     didn
    1.26
     people
    1.25
    Activations Density 0.061%

    No Known Activations