© 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. 34-GEMMASCOPE-RES-131K
    7. 81234
    Prev
    Next
    INDEX
    Explanations

    original condition

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

    The neuron fires on evaluative, positively framed condition statements (e.g. “a prime example of well maintained”) describing an item’s quality.

    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
     new
    -1.13
     nuevos
    -1.00
     nuevas
    -0.97
     neuen
    -0.96
    new
    -0.90
     nueva
    -0.90
    brand
    -0.88
     جدید
    -0.87
     nouvelles
    -0.87
     nuevo
    -0.86
    POSITIVE LOGITS
     survivor
    1.38
     survivors
    1.23
     rare
    1.23
     example
    1.23
     unrest
    1.16
     rarer
    1.13
    survi
    1.13
     clean
    1.10
     restored
    1.09
     immaculate
    1.08
    Activations Density 0.023%

    No Known Activations