© 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. 48332
    Prev
    Next
    INDEX
    Explanations

    loading states

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

    The neuron responds to code tokens that denote “loading” or UI action indicators (e.g. “Loading…” lines and related method calls).

    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
    While
    -3.64
    Surprisingly
    -3.59
    When
    -3.59
    Despite
    -3.58
    Every
    -3.53
    There
    -3.50
    Shortly
    -3.47
    Nearly
    -3.44
    Both
    -3.38
    After
    -3.34
    POSITIVE LOGITS
    艄
    3.33
    癭
    2.66
    聼
    2.61
    蠑
    2.41
     who
    2.36
    已经在
    2.33
    镬
    2.28
    诓
    2.25
     viſ
    2.22
    鲠
    2.20
    Activations Density 0.001%

    No Known Activations