© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 127998
    Prev
    Next
    INDEX
    Explanations

    The neuron responds to terms that indicate ordering or sequence positions (e.g. first, last, ascending, bottom, comes first).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    order and timing

    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
    😂😂😂😂
    -0.84
    ujú
    -0.82
    🤣🤣🤣
    -0.82
    Mounting
    -0.81
     veta
    -0.79
     suffisamment
    -0.77
     kalender
    -0.75
     båda
    -0.75
    烴
    -0.74
    🤣🤣
    -0.73
    POSITIVE LOGITS
     late
    1.43
     later
    1.34
     early
    1.32
     first
    1.30
     after
    1.13
     parmi
    1.12
     before
    1.10
     earliest
    1.08
     AFTER
    1.07
     earlier
    1.03
    Activations Density 0.049%

    No Known Activations