© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27161
    Prev
    Next
    INDEX
    Explanations

    const path

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

    The neuron primarily detects numeric characters or digit sequences 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
     while
    -1.25
     Changer
    -1.25
    СЫ
    -1.24
    😜
    -1.20
     faſt
    -1.20
    🤨
    -1.19
     departement
    -1.18
     industriel
    -1.18
    ORUS
    -1.16
     Templo
    -1.16
    POSITIVE LOGITS
     reemplazar
    1.23
    انواع
    1.23
    épreuve
    1.22
    fting
    1.20
     STARTED
    1.20
    if
    1.16
    有一定
    1.13
    鸰
    1.09
     elegir
    1.09
    8
    1.09
    Activations Density 0.000%

    No Known Activations