© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33909
    Prev
    Next
    INDEX
    Explanations

    different kinds

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

    The neuron activates on the word “different.”

    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
    や
    -1.66
    を
    -1.59
    それは
    -1.51
     most
    -1.50
    uride
    -1.49
    などを
    -1.48
    と
    -1.47
    umers
    -1.46
    了一些
    -1.44
    があるので
    -1.43
    POSITIVE LOGITS
     different
    2.41
     types
    1.91
    形で
    1.86
    corrhi
    1.77
     farklı
    1.76
    種類の
    1.66
     kinds
    1.61
     variadas
    1.59
    で見る
    1.58
     Each
    1.54
    Activations Density 0.047%

    No Known Activations