© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 66461
    Prev
    Next
    INDEX
    Explanations

    blouse or bacillus

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

    The neuron activates for words related to clothing items (especially "blouse") and biological terms (particularly "Lactobacillus" bacteria).

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on occurrences of the word “blouse.”

    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
    涐
    -2.33
     公园
    -2.30
     glyphicon
    -2.25
    Ꮟ
    -2.09
     teus
    -2.08
    最后由
    -2.06
     orar
    -2.05
    对你
    -2.05
     插图
    -1.99
    事儿
    -1.95
    POSITIVE LOGITS
    高手
    2.14
     Многие
    2.08
    釭
    2.02
     faſt
    2.00
    4
    1.98
    7
    1.97
    9
    1.96
    のですが
    1.95
     prohib
    1.94
     Перейти
    1.94
    Activations Density 0.001%

    No Known Activations