© 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. 34-GEMMASCOPE-RES-131K
    7. 89795
    Prev
    Next
    INDEX
    Explanations

    immunohistochemistry and chemistry

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

    symbols and special characters like parentheses, slashes, and formatting symbols in technical text.

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

    The neuron is primarily triggered by numeric tokens (i.e. sequences of digits representing measurements, codes, or other numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    inosa
    -0.72
     earphones
    -0.69
    ılmıştır
    -0.68
    zino
    -0.68
     THUR
    -0.68
     Y
    -0.66
    VIP
    -0.65
     REFR
    -0.64
     earbuds
    -0.64
     औसत
    -0.64
    POSITIVE LOGITS
     domain
    0.96
     domains
    0.90
    cipy
    0.86
    <>
    0.82
    ricts
    0.82
     Domains
    0.81
    بوك
    0.80
    OMING
    0.79
     Domain
    0.78
    щенный
    0.77
    Activations Density 0.002%

    No Known Activations