© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101801
    Prev
    Next
    INDEX
    Explanations

    list indexing and slicing

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

    numeric values (especially single digits) in mathematical or technical contexts like coordinates, arrays, and data structures.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron is triggered by numeric tokens containing decimal points (i.e. floating‐point numbers).

    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
     that
    -2.70
     the
    -2.17
     at
    -1.98
     this
    -1.98
     what
    -1.87
     which
    -1.86
     all
    -1.84
     of
    -1.77
     both
    -1.75
     our
    -1.70
    POSITIVE LOGITS
    6
    1.63
    4
    1.55
     quantités
    1.55
    8
    1.53
     Descubre
    1.51
    2
    1.50
    這個
    1.50
    另外
    1.48
     Obtén
    1.48
    ка
    1.45
    Activations Density 0.047%

    No Known Activations