© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 65676
    Prev
    Next
    INDEX
    Explanations

    words related to "both" and "systems"

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

    This neuron detects references to a "status" field or Status entity in ORM code (e.g. the Status class and the protected $status property).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     because
    -1.22
     which
    -1.02
     when
    -1.02
     this
    -0.95
     if
    -0.94
     where
    -0.91
     other
    -0.91
     some
    -0.89
     Putting
    -0.88
     When
    -0.87
    POSITIVE LOGITS
     både
    3.22
    both
    2.86
     both
    2.86
     zowel
    2.53
     zarówno
    2.30
     BOTH
    2.25
    BOTH
    2.23
     sowohl
    2.22
    ทั้ง
    2.17
    Both
    2.13
    Activations Density 0.251%

    No Known Activations