© 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. 10-GEMMASCOPE-RES-131K
    7. 118827
    Prev
    Next
    INDEX
    Explanations

    events and announcements

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

    the wording of public invitations or meet-and-greet event announcements, especially specifying hosts, invited guests, and scheduled times.

    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
     сегодня
    -1.52
     Voraussetzung
    -1.45
    Recently
    -1.42
     refroid
    -1.39
    Yesterday
    -1.36
     gegenwär
    -1.34
    Today
    -1.33
    ↵
    -1.31
    értel
    -1.31
    行った
    -1.29
    POSITIVE LOGITS
     for
    2.61
     at
    1.87
    liegende
    1.55
     only
    1.51
     diesem
    1.46
     even
    1.34
     tussen
    1.34
     also
    1.33
     in
    1.32
     or
    1.32
    Activations Density 0.009%

    No Known Activations