© 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. 10-GEMMASCOPE-RES-131K
    7. 13510
    Prev
    Next
    INDEX
    Explanations

    Kardashian and blossoms

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

    This neuron strongly activates on occurrences of “blossom” (and its morphological variants such as blossoms, blossomed).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    尐
    -2.89
    涐
    -2.83
     onCreateView
    -2.69
    🤧
    -2.61
    ܜ
    -2.58
    宬
    -2.55
     ſou
    -2.53
    carnation
    -2.52
     is
    -2.52
     onPostExecute
    -2.50
    POSITIVE LOGITS
    1
    4.78
    ’
    3.84
    {
    3.72
    ↵↵
    3.41
    2
    3.13
     
    2.98
    3
    2.91
    A
    2.86
     Then
    2.77
    8
    2.77
    Activations Density 0.004%

    No Known Activations