© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 28138
    Prev
    Next
    INDEX
    Explanations

    technical systems and concepts

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

    The neuron fires on the main topic noun of a passage—especially technical or domain-specific terms that name the subject under discussion.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    型
    -0.94
    Yard
    -0.93
    They
    -0.90
    2
    -0.89
    где
    -0.86
    Beginning
    -0.85
    8
    -0.85
     to
    -0.84
     руке
    -0.84
     cockpit
    -0.84
    POSITIVE LOGITS
     behalf
    1.76
     ועל
    1.41
     وعلى
    1.02
     basis
    1.00
     occasions
    1.00
     whim
    0.99
    steroids
    0.98
     steroids
    0.92
     occasion
    0.91
    ꜱ
    0.89
    Activations Density 0.215%

    No Known Activations