© 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. 22-GEMMASCOPE-RES-131K
    7. 12966
    Prev
    Next
    INDEX
    Explanations

    years and monetary units

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

    The neuron activates on numerical 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_22/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
     and
    -1.27
    centerTitle
    -1.09
    niego
    -1.09
     serdecznie
    -1.05
    cobacterium
    -1.05
     vanaf
    -1.02
     schon
    -1.02
     Novembre
    -1.01
    več
    -1.00
    に使
    -1.00
    POSITIVE LOGITS
    <0xA3>
    1.16
    着一个
    1.11
    があり
    1.09
    それも
    1.05
    そのため
    1.02
    ¹.
    1.02
    これも
    1.00
    お金
    1.00
    が
    0.99
    出一个
    0.98
    Activations Density 0.003%

    No Known Activations