© 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. 64445
    Prev
    Next
    INDEX
    Explanations

    links and resources

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

    The neuron flags tokens that serve as list or section headings—especially numeric labels and related resource‐list titles.

    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
    rrrrrrrr
    -1.07
    rrrrrr
    -0.94
    ,-.
    -0.91
    hhhhhhhh
    -0.91
    ющийся
    -0.91
     holotype
    -0.90
    zzzz
    -0.88
    vertising
    -0.87
    дії
    -0.85
    ,«
    -0.85
    POSITIVE LOGITS
     resources
    4.31
    resources
    3.22
     websites
    3.05
     links
    3.00
     Resources
    2.94
    Resources
    2.94
     recursos
    2.83
     resource
    2.67
     useful
    2.53
    RESOURCES
    2.41
    Activations Density 0.105%

    No Known Activations