© 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. 10-GEMMASCOPE-RES-131K
    4. 118980
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and examples

    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_10/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
     it
    -1.61
    Pasos
    -1.60
     that
    -1.47
    有任何
    -1.38
     erbjuder
    -1.37
     diseñadores
    -1.36
    Capacidad
    -1.34
    所说的
    -1.32
     jefes
    -1.31
    mycompany
    -1.31
    POSITIVE LOGITS
     könnten
    1.70
     février
    1.48
    ঃ
    1.45
    铪
    1.42
     aeruginosa
    1.41
    digans
    1.40
     और
    1.40
     incomplète
    1.39
    return
    1.38
     by
    1.35
    Activations Density 0.140%

    No Known Activations