© 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. 39377
    Prev
    Next
    INDEX
    Explanations

    negative qualities or problems

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

    The neuron flags substantive content words—especially longer, descriptive nouns and adjectives—rather than common function words.

    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
     of
    -0.96
     Jérusalem
    -0.94
    луб
    -0.91
    пто
    -0.90
     Potential
    -0.88
     última
    -0.88
    ventes
    -0.87
    мато
    -0.86
     actuels
    -0.86
     only
    -0.85
    POSITIVE LOGITS
     and
    1.66
    というか
    1.13
    どころ
    1.09
    訃
    1.09
    ']>
    1.05
    服务的
    1.02
     thậm
    1.00
     hatta
    0.99
    甚至
    0.98
     voire
    0.97
    Activations Density 0.061%

    No Known Activations