© 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. 34-GEMMASCOPE-RES-131K
    4. 75712
    Prev
    Next
    INDEX
    Explanations

    Identifiers in code

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

    The neuron fires on tokens that are identifiers ending in “Id” or “ID.”

    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
    潴
    -0.78
     those
    -0.77
    Kry
    -0.68
    璀
    -0.68
    uyla
    -0.68
     CMO
    -0.66
    EDM
    -0.66
     сте
    -0.66
    сами
    -0.65
     LEYENDO
    -0.65
    POSITIVE LOGITS
    entity
    1.04
    nger
    0.97
    posable
    0.86
    enty
    0.84
    టి
    0.81
     lucid
    0.81
     Implementing
    0.81
     aperto
    0.80
    ítu
    0.79
    Persön
    0.78
    Activations Density 0.025%

    No Known Activations