© 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. 1216
    Prev
    Next
    INDEX
    Explanations

    in the section or paragraph

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

    The neuron fires on the legal-boilerplate phrase “set forth in the.”

    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
     bascul
    -1.05
     véhic
    -0.98
    llavero
    -0.96
    Halaman
    -0.96
     крайне
    -0.94
     représenter
    -0.93
    Both
    -0.93
     obliga
    -0.92
     密码
    -0.92
     fortific
    -0.91
    POSITIVE LOGITS
     this
    1.64
     Section
    1.53
     paragraph
    1.47
    Section
    1.23
     or
    1.23
    paragraph
    1.23
     herein
    1.18
     clause
    1.17
     section
    1.14
     paragraphs
    1.09
    Activations Density 0.037%

    No Known Activations