© 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. 93343
    Prev
    Next
    INDEX
    Explanations

    pricing information and details

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

    The neuron activates on uppercase section headings or titles (e.g. “Pricing,” “Pricing Information,” “Naming”) marking the start of a new document section.

    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
     embora
    -0.88
    скій
    -0.87
    iges
    -0.87
    toarele
    -0.86
    分で
    -0.86
    つは
    -0.84
    Рейтинг
    -0.83
     ardor
    -0.82
     étrangère
    -0.77
    ாள
    -0.77
    POSITIVE LOGITS
     scheme
    1.13
     schemes
    1.08
     decisions
    1.05
    cheme
    0.96
     solusi
    0.93
     information
    0.89
     options
    0.89
     irregularities
    0.88
     for
    0.86
     Schemes
    0.86
    Activations Density 0.044%

    No Known Activations