© 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. 22-GEMMASCOPE-RES-131K
    4. 74957
    Prev
    Next
    INDEX
    Explanations

    explaining or controlling processes

    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
     there
    -1.22
     they
    -1.15
     heridos
    -1.05
     completo
    -1.01
    wdriver
    -0.99
     it
    -0.98
    ousine
    -0.97
    際は
    -0.97
     their
    -0.97
     появится
    -0.94
    POSITIVE LOGITS
    Especially
    1.12
     skrift
    1.09
     sposób
    1.06
     przede
    1.03
    Törté
    1.02
     kabát
    1.01
     الذي
    0.99
     húmedo
    0.98
     adjunto
    0.98
    château
    0.96
    Activations Density 0.321%

    No Known Activations