© 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. 53857
    Prev
    Next
    INDEX
    Explanations

    cum prefix

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

    The neuron responds to the character sequence “cum” appearing as part of a token.

    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
     تعرض
    -0.81
    爍
    -0.75
    Información
    -0.73
     Reglamento
    -0.72
     limitada
    -0.70
    års
    -0.69
    Fabulous
    -0.69
    ➏
    -0.69
    ավ
    -0.68
     بدان
    -0.67
    POSITIVE LOGITS
     Cum
    0.89
     honored
    0.80
    bund
    0.79
     honor
    0.76
    cum
    0.75
    ysis
    0.75
     cum
    0.74
     granulo
    0.73
     culinary
    0.72
     Norman
    0.72
    Activations Density 0.038%

    No Known Activations