© 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. 66490
    Prev
    Next
    INDEX
    Explanations

    retailers and retail goods

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

    This neuron activates on occurrences of “retail” (and its variants like “retails,” “retailers,” etc.).

    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
     him
    -2.14
     they
    -1.98
    \
    -1.83
     that
    -1.72
    イズ
    -1.66
     Basically
    -1.63
    In
    -1.59
    '
    -1.59
     which
    -1.56
     Ultimately
    -1.56
    POSITIVE LOGITS
    Ꮏ
    1.86
    髌
    1.86
    ﮟ
    1.80
     provocó
    1.75
    tipps
    1.67
    doesn
    1.66
     '-
    1.66
     keinen
    1.65
     expedited
    1.65
     cojín
    1.63
    Activations Density 0.010%

    No Known Activations