© 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. 10-GEMMASCOPE-RES-131K
    4. 99932
    Prev
    Next
    INDEX
    Explanations

    ruthenium complexes, triangle, boxing weight

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

    The neuron detects the character sequence “then” (for example in words like “ruthenium”).

    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
     for
    -2.33
     three
    -2.23
     one
    -2.05
     two
    -1.99
     first
    -1.95
     several
    -1.91
     but
    -1.72
     as
    -1.72
     fifteen
    -1.70
     Often
    -1.70
    POSITIVE LOGITS
     Quando
    1.84
    抱怨
    1.67
     imó
    1.64
     momentous
    1.62
    Tuber
    1.61
    </i>
    1.60
     όταν
    1.60
     of
    1.59
     pivotal
    1.59
    為に
    1.55
    Activations Density 0.191%

    No Known Activations