© 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. 95406
    Prev
    Next
    INDEX
    Explanations

    there followed by a verb

    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
     which
    -1.70
    felizmente
    -1.60
    笅
    -1.50
    ায়
    -1.48
     or
    -1.48
    cazione
    -1.46
     〜
    -1.45
     Atau
    -1.44
    atiques
    -1.42
     واتس
    -1.40
    POSITIVE LOGITS
     are
    2.36
    ’
    2.19
     were
    2.03
     
    1.95
     a
    1.87
     is
    1.86
     wasn
    1.77
    一方面
    1.59
     was
    1.59
     ample
    1.54
    Activations Density 0.089%

    No Known Activations