© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 70841
    Prev
    Next
    INDEX
    Explanations

    format specifiers like %e, %p

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

    The neuron is strongly triggered by numeric tokens (digits and decimal‐point number fragments) in code.

    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
     internas
    -1.33
    💃
    -1.29
    tobe
    -1.25
    gradable
    -1.25
    ."/
    -1.24
    🙊
    -1.24
    ℉
    -1.24
    /");
    -1.23
     }>
    -1.23
    ᯾
    -1.22
    POSITIVE LOGITS
     now
    1.49
    ––
    1.36
    ܣ
    1.28
     рассказывает
    1.25
     теперь
    1.25
     inzwischen
    1.20
     Enlarged
    1.20
     Vomiting
    1.19
     Parenthood
    1.17
     mammoth
    1.16
    Activations Density 0.001%

    No Known Activations