© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 105524
    Prev
    Next
    INDEX
    Explanations

    tuber, tubercles, tuberculosis

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

    The neuron detects the word "tuber" and related terms like "tuberculosis" and "tuberculous".

    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
    '
    -2.52
    鈰
    -2.47
     they
    -2.44
    ti
    -2.28
     Republica
    -2.27
     cristian
    -2.19
     continuar
    -2.16
    q
    -2.13
    蕻
    -2.11
     fara
    -2.09
    POSITIVE LOGITS
    你怎么
    2.70
     interplay
    2.67
    罴
    2.56
    我能
    2.50
     Когда
    2.47
     starke
    2.38
    𝙚
    2.31
     Kontext
    2.30
     clásica
    2.28
     Widers
    2.28
    Activations Density 0.006%

    No Known Activations