© 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. 49888
    Prev
    Next
    INDEX
    Explanations

    have + past participle verb

    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
     its
    -2.13
     خودش
    -1.59
    Its
    -1.46
    它的
    -1.38
     jego
    -1.36
    它
    -1.35
     его
    -1.23
     njego
    -1.16
     has
    -1.12
     itself
    -1.12
    POSITIVE LOGITS
     their
    3.95
     themselves
    2.94
    Their
    2.55
    their
    2.25
     leurs
    2.03
     leur
    2.03
     Their
    1.99
     ihren
    1.99
    他们的
    1.98
     их
    1.93
    Activations Density 0.106%

    No Known Activations