© 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. 98592
    Prev
    Next
    INDEX
    Explanations

    part of

    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
    
    -1.08
     oportunidade
    -1.08
    はこちらから
    -1.05
     influência
    -1.05
     quantità
    -1.05
     reflexão
    -1.03
     possibilidade
    -1.02
    verstanden
    -1.02
    tadır
    -1.02
    salsa
    -1.02
    POSITIVE LOGITS
     equation
    1.45
    的一部分
    1.34
     that
    1.15
     strategy
    1.09
     or
    1.08
     incorporate
    1.05
     control
    1.02
     constantly
    1.02
    一部分
    1.01
     keep
    0.98
    Activations Density 0.090%

    No Known Activations