© 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. 67883
    Prev
    Next
    INDEX
    Explanations

    positive adjectives in multiple languages

    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
     by
    -1.87
    
    -1.39
     When
    -1.38
     before
    -1.38
     शुर
    -1.34
     in
    -1.30
     Although
    -1.29
     when
    -1.28
     after
    -1.27
     came
    -1.26
    POSITIVE LOGITS
     hermosos
    1.72
     startling
    1.48
     listos
    1.45
     maravill
    1.45
     deliciosos
    1.39
     cómodo
    1.37
     bewegt
    1.36
     haupts
    1.35
     espectaculares
    1.34
     vyroben
    1.34
    Activations Density 0.006%

    No Known Activations