© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74189
    Prev
    Next
    INDEX
    Explanations

    over the past duration

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects temporal‐duration phrases that start with “Over the past” (or similar) followed by a quantified time span.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     to
    -2.39
     two
    -2.22
     when
    -2.00
     as
    -1.91
     because
    -1.90
     use
    -1.88
    S
    -1.88
    A
    -1.84
     S
    -1.83
     P
    -1.82
    POSITIVE LOGITS
     siè
    1.91
     sés
    1.73
    liegende
    1.70
    Tämä
    1.70
     péché
    1.67
    quelles
    1.64
    chtete
    1.63
     uſ
    1.63
     vérification
    1.63
     segítség
    1.62
    Activations Density 0.026%

    No Known Activations