© 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. 75342
    Prev
    Next
    INDEX
    Explanations

    math and programming expressions

    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
    ったのは
    -1.23
     other
    -1.21
     still
    -1.09
     your
    -1.05
    einem
    -1.04
     also
    -1.02
     castillo
    -1.02
    Šaltiniai
    -1.00
     целью
    -1.00
     Development
    -1.00
    POSITIVE LOGITS
    ättning
    1.05
     inexorable
    1.02
     orgas
    1.01
     Verne
    1.00
     ento
    0.99
     neigh
    0.98
     spotify
    0.97
     carbo
    0.97
    群馬
    0.97
     VIV
    0.97
    Activations Density 0.003%

    No Known Activations