© 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. 98
    Prev
    Next
    INDEX
    Explanations

    time expressions followed by context

    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
     informace
    -1.61
     popis
    -1.46
     анге
    -1.45
     ecran
    -1.45
    と思いました
    -1.41
     umožňuje
    -1.41
     textu
    -1.41
     pomoci
    -1.39
     занимается
    -1.39
     принял
    -1.38
    POSITIVE LOGITS
     of
    5.06
     they
    2.88
     you
    2.64
     it
    2.48
     we
    2.30
     that
    2.25
     που
    1.53
     he
    1.47
     who
    1.41
     The
    1.38
    Activations Density 0.017%

    No Known Activations