© 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. 11822
    Prev
    Next
    INDEX
    Explanations

    taco, Taco Bell, Lactobacillus

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

    food-related words, particularly "taco" and related Mexican food terms.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    -3.55
    '
    -2.61
     dobrý
    -2.61
    潆
    -2.56
    鹮
    -2.53
    ますが
    -2.52
    3
    -2.48
    9
    -2.47
    的一個
    -2.41
    聼
    -2.38
    POSITIVE LOGITS
    栳
    2.92
    𓋼
    2.72
     ';
    2.56
    銠
    2.41
    葙
    2.41
    ⅰ
    2.34
     faſt
    2.27
    ?」
    2.27
    蛩
    2.27
    蟶
    2.25
    Activations Density 0.002%

    No Known Activations