© 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. 34-GEMMASCOPE-RES-131K
    4. 110997
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names

    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_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
     réinitial
    -2.20
     rapporter
    -2.02
     réve
    -2.00
    ølge
    -1.95
    moiselle
    -1.95
     kän
    -1.92
     itali
    -1.91
     vulgaires
    -1.87
     brosse
    -1.87
     öf
    -1.80
    POSITIVE LOGITS
     a
    2.13
     for
    2.09
     and
    1.91
     to
    1.91
     M
    1.81
     such
    1.81
    ...
    1.76
     D
    1.66
     S
    1.65
     T
    1.65
    Activations Density 0.002%

    No Known Activations