© 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. 73855
    Prev
    Next
    INDEX
    Explanations

    conjunctions and transitions

    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
    tablir
    -0.88
    entown
    -0.86
    ziału
    -0.86
    felizmente
    -0.85
    blis
    -0.84
     arrivé
    -0.84
    zzie
    -0.84
    呲
    -0.84
     andere
    -0.83
    panes
    -0.83
    POSITIVE LOGITS
     here
    1.04
     Suomessa
    0.87
     aplicado
    0.86
    Based
    0.85
    Accordingly
    0.83
     możemy
    0.83
     Quindi
    0.83
    Föld
    0.82
     getApplication
    0.81
    今回は
    0.81
    Activations Density 0.037%

    No Known Activations