© 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. 10913
    Prev
    Next
    INDEX
    Explanations

    numbers and operands

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

    The neuron is tuned to spot numeric tokens and digit sequences (numbers and arithmetic expressions) 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_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
    -1.30
     started
    -1.01
    México
    -1.00
    Odpowiedz
    -0.98
     officially
    -0.96
     while
    -0.93
    之所
    -0.92
     choices
    -0.92
    ğim
    -0.91
     options
    -0.90
    POSITIVE LOGITS
     étrange
    1.20
     Ceux
    1.13
    ？』
    1.06
     erzielt
    1.05
     Jusqu
    1.05
     aussitôt
    1.04
    IFYING
    1.04
    vité
    1.03
    "];
    1.02
     clôture
    1.02
    Activations Density 0.000%

    No Known Activations