© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63712
    Prev
    Next
    INDEX
    Explanations

    science fiction authors

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

    The neuron is keyed to numeric reference tokens—especially years, issue numbers, and numbers in parentheses in citations.

    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
    xmlns
    -0.85
     Friendship
    -0.82
     requ
    -0.79
    funeralhome
    -0.76
    itering
    -0.76
    INDIAN
    -0.75
    mirante
    -0.74
     friendship
    -0.74
    チナ
    -0.74
     Mozambique
    -0.73
    POSITIVE LOGITS
     Wells
    1.14
     HG
    1.06
    Wells
    0.92
     Machine
    0.81
     WELLS
    0.79
    HG
    0.78
     specifico
    0.77
     invasions
    0.77
    wells
    0.76
    Machine
    0.75
    Activations Density 0.037%

    No Known Activations