© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 39740
    Prev
    Next
    INDEX
    Explanations

    journal citation numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     like
    -0.96
     Nieuws
    -0.87
    orientation
    -0.87
     AUTHORITIES
    -0.85
    íny
    -0.85
    planted
    -0.85
    =="
    -0.84
    😳
    -0.84
     Kombat
    -0.84
     berdasarkan
    -0.83
    POSITIVE LOGITS
     microbiome
    1.09
    Хорошо
    0.97
     benö
    0.97
     набор
    0.91
     hashtag
    0.91
    grimas
    0.89
     selfies
    0.88
     relinqu
    0.88
     często
    0.88
     bazı
    0.88
    Activations Density 0.002%

    No Known Activations