© 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. 34-GEMMASCOPE-RES-131K
    7. 48661
    Prev
    Next
    INDEX
    Explanations

    known for

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

    The neuron fires on the “known for” construction (and its variants like “not only … but also”) used to introduce what someone or something is recognized for.

    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
     ocorre
    -0.94
     joga
    -0.94
     completely
    -0.93
     those
    -0.93
     concorda
    -0.92
     what
    -0.91
    thaler
    -0.90
     abar
    -0.90
     inspired
    -0.88
    RICULUM
    -0.87
    POSITIVE LOGITS
     for
    2.20
     by
    1.48
     among
    1.21
     blant
    1.08
     as
    1.02
    遐
    1.02
    ことで
    0.99
     amongst
    0.98
     για
    0.96
     throughout
    0.96
    Activations Density 0.054%

    No Known Activations