© 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. 83428
    Prev
    Next
    INDEX
    Explanations

    conjunctions and punctuation

    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
     altså
    -1.00
     Như
    -0.87
    enix
    -0.87
    ready
    -0.87
    URY
    -0.84
    diğini
    -0.80
     peered
    -0.79
    की
    -0.78
    zsche
    -0.78
    別に
    -0.77
    POSITIVE LOGITS
     поэтому
    5.81
     therefore
    5.78
     deshalb
    4.69
     Therefore
    4.59
    Therefore
    4.53
     dlatego
    4.53
     daarom
    4.41
     Поэтому
    4.31
     derfor
    4.31
    因此
    4.25
    Activations Density 0.011%

    No Known Activations