© 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. 13134
    Prev
    Next
    INDEX
    Explanations

    technical code snippets

    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
     on
    -1.43
     any
    -1.30
     two
    -1.27
     both
    -1.27
     what
    -1.26
     their
    -1.25
     or
    -1.20
     removes
    -1.20
     for
    -1.20
     allows
    -1.19
    POSITIVE LOGITS
     opulent
    1.16
     Dinas
    1.14
     horrid
    1.11
     aristocrat
    1.08
     😁
    1.08
     russell
    1.06
     famed
    1.05
     おしゃれ
    1.05
     dette
    1.05
     queste
    1.05
    Activations Density 0.010%

    No Known Activations