© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 129331
    Prev
    Next
    INDEX
    Explanations

    ascending or decreasing order

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

    The neuron detects words and phrases that specify sequence ordering—particularly “ascending,” “descending” (or “decreasing”), and “order.”

    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
     seleccionados
    -1.65
    さてさて
    -1.55
    廰
    -1.52
     ¨
    -1.49
    スポンサーリンク
    -1.49
     vanden
    -1.48
    Staying
    -1.48
    냑
    -1.48
     ď
    -1.48
     …..
    -1.47
    POSITIVE LOGITS
     with
    1.79
    </h3>
    1.66
     or
    1.61
     using
    1.59
     and
    1.59
     vitales
    1.49
     at
    1.48
     We
    1.47
     for
    1.42
    er
    1.41
    Activations Density 0.036%

    No Known Activations