© 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. 34-GEMMASCOPE-RES-131K
    7. 6866
    Prev
    Next
    INDEX
    Explanations

    thousands and millions

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

    The neuron fires on numeric tokens—i.e. occurrences of numbers or multi-digit numerals in the text.

    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
     that
    -0.89
     also
    -0.89
     just
    -0.83
     not
    -0.82
     doz
    -0.81
     grill
    -0.81
    ерез
    -0.80
    MockBean
    -0.79
     mercy
    -0.77
     redesign
    -0.77
    POSITIVE LOGITS
     schonmal
    1.13
     thousand
    1.06
     тыся
    1.00
    抠
    0.94
     anfangs
    0.92
     milliers
    0.91
     천
    0.91
    êm
    0.90
    <0x80>
    0.90
    还是很
    0.90
    Activations Density 0.019%

    No Known Activations