© 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. 34-GEMMASCOPE-RES-131K
    7. 63919
    Prev
    Next
    INDEX
    Explanations

    bug, date, and technical identifiers

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

    The neuron is detecting long sequences of digits (numeric IDs or other multi‐digit 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_34/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
     Transformers
    -0.76
    createQuery
    -0.76
     نوفمبر
    -0.75
    PlayerPrefs
    -0.73
     Lash
    -0.70
    BufferedWriter
    -0.69
     föres
    -0.69
    IActionResult
    -0.68
     Pray
    -0.66
    jsonArray
    -0.66
    POSITIVE LOGITS
    をご紹介します
    0.75
    beri
    0.74
     Unger
    0.73
    Atención
    0.68
     органов
    0.68
     बहुत
    0.67
     tag
    0.66
    Enums
    0.66
     беше
    0.66
     органы
    0.65
    Activations Density 0.051%

    No Known Activations