© 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. 10-GEMMASCOPE-RES-131K
    7. 60259
    Prev
    Next
    INDEX
    Explanations

    high degrees of complexity or abundance

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

    The neuron fires strongest on descriptive adjectives and adverbs that convey degree or intensity.

    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
     pretende
    -1.60
     genellikle
    -1.53
     présents
    -1.53
     realmente
    -1.50
     blatant
    -1.48
    崤
    -1.47
    大腿
    -1.47
    uniqlo
    -1.45
    xvii
    -1.44
     birbir
    -1.42
    POSITIVE LOGITS
    ization
    1.89
    ÁRIO
    1.88
    、
    1.78
    i
    1.74
    e
    1.73
    a
    1.66
     invigor
    1.55
    彣
    1.55
     Taking
    1.55
     Eight
    1.54
    Activations Density 0.016%

    No Known Activations