© 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. 34-GEMMASCOPE-RES-131K
    4. 55746
    Prev
    Next
    INDEX
    Explanations

    MySQL code

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

    The neuron is highly sensitive to numeric tokens, especially standalone numbers and version or year references in code and license 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_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
     Steele
    -0.74
     SCAN
    -0.72
    NotNull
    -0.72
     Casey
    -0.71
    パク
    -0.67
     Energía
    -0.67
     Scanner
    -0.67
    ばい
    -0.67
    学的
    -0.66
     Lulu
    -0.66
    POSITIVE LOGITS
    漢
    0.69
    EINVAL
    0.66
    HQ
    0.66
     dans
    0.65
    調整
    0.65
     готова
    0.65
    未満
    0.64
     פרי
    0.64
     Contributions
    0.63
    listado
    0.63
    Activations Density 0.075%

    No Known Activations