© 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. 39087
    Prev
    Next
    INDEX
    Explanations

    largest [noun]

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

    The neuron activates on superlative size or rank phrases, especially occurrences of “largest.”

    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
     should
    -1.51
     that
    -1.32
     gemeint
    -1.26
    This
    -1.23
     generally
    -1.21
     aquellas
    -1.21
     seems
    -1.18
    大部分
    -1.17
     improves
    -1.14
     This
    -1.11
    POSITIVE LOGITS
    complish
    1.38
    largest
    1.36
     monstre
    1.26
     durer
    1.15
    Largest
    1.15
    一旁
    1.13
     largest
    1.13
    规模
    1.11
    prechen
    1.09
     ਵਿੱਚ
    1.09
    Activations Density 0.045%

    No Known Activations