© 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. 22-GEMMASCOPE-RES-131K
    7. 15780
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements

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

    The neuron fires on numeric tokens and financial figures (digits, multi‐digit numbers, decimals, percentages, prices, index values).

    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
     to
    -1.48
     like
    -1.33
     ".
    -1.29
     '
    -1.19
    !
    -1.16
     such
    -1.13
     '.
    -1.08
     './../
    -1.08
     \&
    -1.06
    _
    -1.02
    POSITIVE LOGITS
     akumulator
    1.20
    ѧ
    1.13
    ībā
    1.12
    üyor
    1.11
     sukienka
    1.10
    französ
    1.10
     chì
    1.09
    还是很
    1.09
    依旧
    1.08
    什么事
    1.07
    Activations Density 0.006%

    No Known Activations