© 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. 10-GEMMASCOPE-RES-131K
    7. 44676
    Prev
    Next
    INDEX
    Explanations

    quantifiers followed by nouns

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

    The neuron activates on numeric tokens that include a decimal point (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
     or
    -2.84
     in
    -2.08
     make
    -1.92
     both
    -1.88
     would
    -1.88
     gives
    -1.84
     makes
    -1.83
     give
    -1.82
     gave
    -1.80
     with
    -1.79
    POSITIVE LOGITS
    genodigd
    1.73
    辚
    1.73
     Dinas
    1.61
     revered
    1.59
    mbgg
    1.58
     unbelievably
    1.57
    ادامه
    1.56
     célè
    1.56
     lauded
    1.52
     mauva
    1.52
    Activations Density 0.141%

    No Known Activations