© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 56999
    Prev
    Next
    INDEX
    Explanations

    actions or requirements

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

    The neuron flags the key content words—primarily core action verbs or technical nouns—that signal the main focus of a question or instruction.

    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
    ウンテン
    -0.92
    still
    -0.91
    hanced
    -0.86
    nof
    -0.84
    ース
    -0.82
    ateľ
    -0.81
    herent
    -0.80
    itize
    -0.79
    upon
    -0.78
    Aplicación
    -0.78
    POSITIVE LOGITS
     mechanism
    0.99
    ness
    0.97
     occupies
    0.91
    率
    0.90
     occurs
    0.90
    琪
    0.88
     occurred
    0.88
     zwem
    0.87
    方式
    0.85
     should
    0.84
    Activations Density 0.263%

    No Known Activations