© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130019
    Prev
    Next
    INDEX
    Explanations

    The neuron looks for terms that express quantitative change or comparison (e.g. increase, decrease, difference, greater).

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

    consequently, correspondingly, likewise

    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
     überhaupt
    -0.81
    ষ
    -0.79
    vincent
    -0.78
    patu
    -0.78
    kunt
    -0.78
     ziel
    -0.77
     Otras
    -0.77
    ulte
    -0.77
     вообще
    -0.76
    malte
    -0.75
    POSITIVE LOGITS
     correspondingly
    1.74
     likewise
    1.49
     accordingly
    1.30
    随之
    1.22
     corresponding
    1.20
     consequently
    1.20
     too
    1.16
    相应
    1.11
    Likewise
    1.09
     Likewise
    1.08
    Activations Density 0.107%

    No Known Activations