© 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. 10-GEMMASCOPE-RES-131K
    7. 111030
    Prev
    Next
    INDEX
    Explanations

    floating things

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

    The neuron fires on occurrences of the word “Floating” (e.g., as a standalone token or in technical names).

    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
    1
    -2.53
     meravigli
    -2.38
    2
    -2.28
     they
    -2.27
     PERFECT
    -2.25
    餮
    -2.25
    9
    -2.22
     остальные
    -2.20
    ING
    -2.19
    導致
    -2.17
    POSITIVE LOGITS
    ୌ
    2.95
     Each
    2.91
     unconventional
    2.80
    沇
    2.78
     hilarious
    2.70
     multifaceted
    2.70
    ～～
    2.66
    取締
    2.64
     نمی‌
    2.61
    以上就是
    2.59
    Activations Density 0.006%

    No Known Activations