© 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. 36185
    Prev
    Next
    INDEX
    Explanations

    code snippets and configurations

    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
     regn
    -1.12
    
    -1.02
    礡
    -1.01
     imobili
    -0.99
     tremend
    -0.99
     pior
    -0.99
     corret
    -0.99
     SPF
    -0.98
     concor
    -0.96
    ADOR
    -0.96
    POSITIVE LOGITS
     Если
    1.08
     OGSÅ
    1.00
     verschiedenen
    0.98
     habrían
    0.96
     If
    0.95
    ↵↵↵
    0.95
     debía
    0.93
    !
    0.92
    已经
    0.92
     discussão
    0.92
    Activations Density 0.024%

    No Known Activations