© 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. 92351
    Prev
    Next
    INDEX
    Explanations

    archaic pronouns and quotes

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

    The neuron fires on direct quotations from scripture passages—i.e. blocks of speech immediately following a verse reference.

    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
     every
    -0.94
     their
    -0.92
     February
    -0.89
     people
    -0.87
    🩴
    -0.85
     less
    -0.85
     when
    -0.84
     always
    -0.84
     klarer
    -0.84
     during
    -0.82
    POSITIVE LOGITS
    yesterday
    1.13
    myself
    0.97
     yonder
    0.93
    Zed
    0.91
     ridu
    0.90
     Nga
    0.88
    рованы
    0.87
    给我们
    0.86
    NIC
    0.86
     اختیار
    0.85
    Activations Density 0.014%

    No Known Activations