© 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. 12666
    Prev
    Next
    INDEX
    Explanations

    Angelenos, Angolan, Angiotensin, Angiogenesis

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

    The neuron detects the prefix "Angio" which appears in medical/biological terms like angiogenesis and geographical names like Angola.

    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
    先は
    -2.91
    CHREIB
    -2.89
    雳
    -2.59
    uatan
    -2.56
    縂
    -2.52
    瑒
    -2.45
    끫
    -2.44
    lardan
    -2.42
    
    -2.42
    ఞ
    -2.39
    POSITIVE LOGITS
    s
    4.06
    a
    3.28
     {
    3.25
    _
    2.98
     â
    2.80
    ised
    2.77
    d
    2.75
     {\
    2.73
     =
    2.72
     of
    2.70
    Activations Density 0.015%

    No Known Activations