© 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. 34-GEMMASCOPE-RES-131K
    7. 302
    Prev
    Next
    INDEX
    Explanations

    citation markers and code structures

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

    The neuron flags numeric tokens—i.e. standalone numbers or numeric identifiers—throughout 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_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
     bych
    -0.84
    ニョ
    -0.71
     veulent
    -0.70
    ቲ
    -0.69
    OwnProperty
    -0.69
     accessibles
    -0.69
    يوب
    -0.68
     целом
    -0.67
     xPos
    -0.67
     abraz
    -0.67
    POSITIVE LOGITS
    Israel
    0.90
    Ό
    0.86
     sprinter
    0.79
    Glad
    0.78
    WORTH
    0.78
    âl
    0.77
     Rapper
    0.77
     laf
    0.76
    ETHYL
    0.76
    čke
    0.76
    Activations Density 0.224%

    No Known Activations