© 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. 437
    Prev
    Next
    INDEX
    Explanations

    xml tags and code constructs

    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
     many
    -1.19
    就去
    -1.11
     those
    -1.05
     I
    -1.02
     my
    -1.01
     consider
    -1.01
     several
    -1.00
     some
    -0.98
     previously
    -0.97
     last
    -0.93
    POSITIVE LOGITS
    yarnpkg
    1.09
    eynman
    1.07
     Berikut
    1.07
     آید
    1.05
     Terkait
    1.05
     accompagner
    1.05
    軼
    1.05
    ፤
    1.04
    Terug
    1.03
    excellents
    1.02
    Activations Density 0.002%

    No Known Activations