© 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. 34-GEMMASCOPE-RES-131K
    7. 49424
    Prev
    Next
    INDEX
    Explanations

    beyond, just, besides, trumps, than

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

    The neuron detects subjective hedging and qualifier words expressing uncertainty or emphasis (e.g. think, seems, just, merely, goes beyond).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     estimate
    -0.91
    Technologies
    -0.89
    Jing
    -0.88
    ・)
    -0.86
    Ethnic
    -0.86
    ском
    -0.84
    ższe
    -0.83
     جامعة
    -0.83
     Wij
    -0.82
    rénées
    -0.81
    POSITIVE LOGITS
     how
    1.44
     having
    1.36
     lack
    1.25
     being
    1.23
     geography
    1.21
    เรื่อง
    1.19
     location
    1.17
    geography
    1.17
     needing
    1.17
     the
    1.14
    Activations Density 0.082%

    No Known Activations