© 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. 39962
    Prev
    Next
    INDEX
    Explanations

    software component names

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

    The neuron strongly activates on numeric tokens (whole numbers and decimals) appearing in code or text, such as version numbers, copyright years, identifiers, and other standalone digits.

    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
     люблю
    -1.09
     both
    -1.08
     should
    -1.03
    neous
    -1.00
    nico
    -1.00
     serupa
    -0.99
    ünk
    -0.98
     asfalto
    -0.98
    āda
    -0.98
    囑
    -0.97
    POSITIVE LOGITS
    ,\\
    1.13
    !,
    1.13
    ി
    1.12
    ,"
    1.09
    '.
    1.08
    ,
    1.07
    ®,
    1.04
    "¿
    1.02
    ator
    1.01
     $\&$
    1.01
    Activations Density 0.076%

    No Known Activations