© 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. 127180
    Prev
    Next
    INDEX
    Explanations

    disulfide bonds or bam

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

    acronyms and technical terms in scientific or programming contexts.

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

    The neuron is keyed to small technical identifiers—short uppercase or mixed‐case abbreviations and code or biochemical names (e.g. “bam_…”, “AIC”, “Bam” restriction sites, “disulfide”).

    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
    他
    -2.98
    梠
    -2.88
    𖣘
    -2.73
     którzy
    -2.64
     citado
    -2.55
    喾
    -2.52
    ি
    -2.52
     蓋
    -2.50
     reduce
    -2.50
    इटम
    -2.47
    POSITIVE LOGITS
    or
    2.59
    注意事
    2.30
     --
    2.20
    o
    2.20
     is
    2.19
    ⢓
    2.19
    as
    2.16
    0
    2.11
         
    2.08
    ?"
    2.03
    Activations Density 0.008%

    No Known Activations