© 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. 70836
    Prev
    Next
    INDEX
    Explanations

    Design, Synthesis, Covers

    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
     this
    -1.00
     on
    -0.99
     awhile
    -0.96
     around
    -0.94
     with
    -0.93
     while
    -0.93
    もちゃ
    -0.93
     extérieur
    -0.93
    餡
    -0.88
     as
    -0.86
    POSITIVE LOGITS
     Faça
    1.01
    からお
    0.94
     Propriété
    0.90
    をかける
    0.85
     BER
    0.83
    JoinColumn
    0.82
    Peng
    0.81
     Diabetes
    0.81
    éton
    0.81
     œ
    0.81
    Activations Density 0.024%

    No Known Activations