© 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. 68017
    Prev
    Next
    INDEX
    Explanations

    software versions and libraries

    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
     sufficient
    -1.20
     different
    -1.17
     only
    -1.17
    にします
    -1.14
     vuole
    -1.06
     it
    -1.03
     ample
    -1.03
    ときは
    -1.03
    ようになって
    -1.02
     appunto
    -1.01
    POSITIVE LOGITS
    öyle
    1.20
    
    1.17
    セリフ
    1.14
    ttää
    1.12
    ificantly
    1.12
    Élet
    1.11
    🏢
    1.08
     reiz
    1.06
    tall
    1.06
    komme
    1.05
    Activations Density 0.091%

    No Known Activations