© 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. 7136
    Prev
    Next
    INDEX
    Explanations

    temporal clauses marked by "when"

    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
    また
    -1.03
    その
    -0.91
     to
    -0.91
     a
    -0.91
     ciò
    -0.90
     also
    -0.90
    ところ
    -0.84
     that
    -0.83
     daug
    -0.82
     places
    -0.81
    POSITIVE LOGITS
     when
    1.63
     kdy
    1.39
     kiedy
    1.31
     podczas
    1.19
     یعنی
    1.17
    During
    1.17
     عندما
    1.09
     During
    1.03
     after
    1.02
     during
    1.02
    Activations Density 0.040%

    No Known Activations