© 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. 59438
    Prev
    Next
    INDEX
    Explanations

    web-related prefixes and common words

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

    The neuron strongly activates on the standalone preposition “of.”

    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
     sweep
    -0.72
     dropdown
    -0.71
    ┄
    -0.69
    getTarget
    -0.69
    %=
    -0.68
     circulación
    -0.68
     sweeps
    -0.68
    lö
    -0.68
     coordinación
    -0.67
     fortsätter
    -0.67
    POSITIVE LOGITS
    שׁ
    0.71
    ogueira
    0.67
    รง
    0.66
     Benth
    0.65
     ninja
    0.65
    upassen
    0.64
    alnya
    0.64
     こ
    0.62
    cepan
    0.62
    integra
    0.62
    Activations Density 0.057%

    No Known Activations