© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1816
    Prev
    Next
    INDEX
    Explanations

    ubiquitin conjugation and synthesis

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

    terms related to biochemical processes, particularly ubiquitin ligases and enzymatic activities.

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

    The neuron fires on occurrences of the biochemical term “ubiquitin” (and its derivatives such as ubiquitination or ubiquitin‐conjugating).

    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
     degra
    -0.91
    pherd
    -0.77
    degener
    -0.76
    Nep
    -0.74
    Hound
    -0.73
    δι
    -0.73
    DOG
    -0.73
    ramen
    -0.70
     Ruskin
    -0.69
     exporters
    -0.68
    POSITIVE LOGITS
     conjug
    0.83
    imia
    0.78
     Conjug
    0.77
     tightening
    0.76
    )>>
    0.73
     Attachment
    0.73
    tom
    0.72
     conjugation
    0.72
    Multiline
    0.71
    wa
    0.71
    Activations Density 0.139%

    No Known Activations